{
  "$schema": "https://readbeforerun.ai/schema/entry.schema.json",
  "entry": {
    "id": "accessitgroup-webapp-testing-checklist",
    "name": "Webapp Testing Checklist",
    "summary": "Agent skill that walks an authorized web application test through the OWASP WSTG checklist and writes a findings report.",
    "draft": "review",
    "type": "skill",
    "mission": [
      "offensive"
    ],
    "task": [
      "web-api-testing"
    ],
    "domain": [
      "application-security"
    ],
    "runtime": [
      "claude-code"
    ],
    "tier": "listed",
    "last_checked": "2026-10-21",
    "next_check": "2027-01-19",
    "freshness": "fresh",
    "superseded": false,
    "in_my_kit": null,
    "advice": null,
    "code_shows": "adds autostart, users or keys · writes outside the project · runs shell commands or eval · reads broad tokens or the environment · Approval: unknown",
    "source": {
      "repo": "https://github.com/AccessITGroup/webapp-testing-checklist",
      "subpath": null,
      "commit": "d79e59434bb7d3ddc61629e3cced9b55ffbaf39b",
      "version": null,
      "license": "MIT AND CC-BY-SA-4.0"
    },
    "install": {
      "skills_cli": null,
      "claude_code": null,
      "upstream": "/plugin marketplace add AccessITGroup/claude-plugins\n/plugin install webapp-testing-checklist@AITG-hub",
      "bundled": false
    },
    "scan": {
      "status": "static scan pending (not run)"
    },
    "reach": {
      "method": "reach-v0.1",
      "level": 3,
      "level_source": "static",
      "level_label": "privileged",
      "unknown_axes": 1,
      "verdict": "not-run",
      "badge": "reach 3 · not run yet",
      "long": "reach 3 from code (privileged); lab: not run yet",
      "declared": {
        "fs": 2,
        "net": 1,
        "exec": 1,
        "cred": 2,
        "persist": 3
      },
      "static": {
        "level": 3,
        "fs": 2,
        "net": 1,
        "exec": 2,
        "cred": 2,
        "persist": 3,
        "hitl": null,
        "unknown": [
          "hitl"
        ]
      },
      "observed": null,
      "surplus": null,
      "fit": null,
      "exports": {
        "aivss": {
          "fs": 0.5,
          "net": 0.5,
          "exec": 0.5,
          "cred": 0.5,
          "persist": 1,
          "hitl": null
        },
        "usf_risk_tier": "L3"
      }
    },
    "profile": {
      "read_at": "d79e59434bb7d3ddc61629e3cced9b55ffbaf39b",
      "read_on": "2026-10-25",
      "overview": "A skill that walks a web application penetration test through the OWASP Web Security Testing Guide (WSTG) as a structured checklist and produces WSTG-numbered findings. It aids a human-led engagement: it may send benign traffic, while attack testing stays with the tester's own tooling.",
      "purpose": [
        "Structures an authorized web application penetration test around the OWASP WSTG methodology and tracks checklist coverage.",
        "Turns tester-supplied evidence into a findings report with WSTG-numbered IDs.",
        "Asks a diagnostic question per WSTG test and interprets the evidence the tester hands over, including raw Burp/ZAP captures."
      ],
      "use_cases": [
        {
          "text": "Plan, scope or track a web application pentest against the WSTG checklist.",
          "task": "web-api-testing"
        },
        {
          "text": "Produce a findings report with WSTG IDs in Markdown, Word (.docx) or PDF.",
          "task": "web-api-testing"
        },
        {
          "text": "Assess tester-supplied request/response evidence against a WSTG test's criteria and record the verdict.",
          "task": "finding-validation"
        },
        {
          "text": "Walk an API-only target through API Testing plus the API-relevant tests from Authentication, Session, Input Validation and Business Logic.",
          "task": "web-api-testing"
        }
      ],
      "maturity": null,
      "capabilities": [
        {
          "name": "Step 1 — Authorization gate",
          "effects": [],
          "enabled": "default"
        },
        {
          "name": "Test credentials file",
          "effects": [
            "reads"
          ],
          "enabled": "default"
        },
        {
          "name": "Step 2 — Scope intake",
          "effects": [],
          "enabled": "default"
        },
        {
          "name": "Step 3 — Walk the checklist",
          "effects": [
            "reads"
          ],
          "enabled": "default"
        },
        {
          "name": "Evidence directory convention",
          "effects": [
            "reads",
            "changes"
          ],
          "enabled": "default"
        },
        {
          "name": "Self-tested findings",
          "effects": [
            "reads",
            "changes"
          ],
          "enabled": "default"
        },
        {
          "name": "Backseat mode benign traffic",
          "effects": [
            "reads",
            "sends-data"
          ],
          "enabled": "default"
        },
        {
          "name": "Account creation (gated)",
          "effects": [
            "changes"
          ],
          "enabled": "optional"
        },
        {
          "name": "Repeated-attempt tests",
          "effects": [
            "sends-data"
          ],
          "enabled": "optional"
        },
        {
          "name": "Step 4 — Report",
          "effects": [
            "changes"
          ],
          "enabled": "default"
        }
      ],
      "effects": [
        "reads",
        "changes",
        "sends-data"
      ],
      "runs": "in-client",
      "listens": [],
      "sends_to": [
        {
          "to": "Target web application",
          "kind": "target",
          "when": "default"
        }
      ],
      "model": "client",
      "needs": [
        {
          "kind": "runtime",
          "text": "Claude Code, with the skill installed from the AITG-hub marketplace or directly."
        },
        {
          "kind": "authorization",
          "text": "Written authorization to test the specific target, such as a signed SOW or pentest agreement."
        },
        {
          "kind": "authorization",
          "text": "Named engagement, in-scope hostnames/apps/IP ranges, testing window and rules of engagement with points of contact."
        },
        {
          "kind": "credentials",
          "text": "Test accounts in a plain-text file in the working directory, one per line with label, role, username and password."
        },
        {
          "kind": "tools",
          "text": "The tester's own testing tools, such as Burp Suite, ZAP, curl or browser devtools, for the actual security testing."
        },
        {
          "kind": "tools",
          "text": "For .docx reports with screenshots, the author reports pandoc or python-docx, where available, as more reliable than OS-builtin converters."
        },
        {
          "kind": "tools",
          "text": "Screenshots of self-tested findings need a visual or browser-automation capability in the environment, not just a CLI HTTP client."
        }
      ]
    },
    "urls": {
      "page": "/catalog/accessitgroup-webapp-testing-checklist/",
      "json": "/entries/accessitgroup-webapp-testing-checklist.json",
      "md": "/catalog/accessitgroup-webapp-testing-checklist.md",
      "badge": "/badge/accessitgroup-webapp-testing-checklist.svg"
    }
  },
  "data": {
    "schema_version": "0.5",
    "slug": "accessitgroup-webapp-testing-checklist",
    "name": "Webapp Testing Checklist",
    "summary": "Agent skill that walks an authorized web application test through the OWASP WSTG checklist and writes a findings report.",
    "draft": "review",
    "in_my_kit": null,
    "type": "skill",
    "mission": [
      "offensive"
    ],
    "task": [
      "web-api-testing"
    ],
    "domain": [
      "application-security"
    ],
    "phase": [
      "off:recon",
      "off:validation",
      "off:reporting"
    ],
    "role": [
      "pentest",
      "appsec"
    ],
    "runtime": [
      "claude-code"
    ],
    "auth": null,
    "autonomy": null,
    "addresses": [],
    "frameworks": {
      "owasp_ast": [],
      "owasp_asi": [],
      "attack_tactic": [],
      "atlas": []
    },
    "source": {
      "repo": "https://github.com/AccessITGroup/webapp-testing-checklist",
      "commit": "d79e59434bb7d3ddc61629e3cced9b55ffbaf39b",
      "license": "MIT AND CC-BY-SA-4.0",
      "manifest": "SKILL.md",
      "also_listed": {
        "tenable-cyberagents-exchange": "https://github.com/tenable/cyberagents-exchange/blob/9d0ddf1fe8dc9651a0c461a2a27d33cb8a160a2c/skills/webapp-testing-checklist.md"
      }
    },
    "upstream": {
      "checked_at": "2026-10-21",
      "updated_at": "2026-09-03",
      "current_release": null,
      "archived": false,
      "stars": 9,
      "commit_history": {},
      "releases_since_pin": 0
    },
    "install": {
      "upstream": "/plugin marketplace add AccessITGroup/claude-plugins\n/plugin install webapp-testing-checklist@AITG-hub",
      "upstream_evidence": "README.md#L60-64",
      "bundled": false
    },
    "scan": [
      {
        "tool": "cisco-skill-scanner",
        "version": "not-run",
        "llm_judge": false,
        "date": "2026-10-21",
        "result": "pending"
      }
    ],
    "privileges": {
      "method": "reach-v0.1",
      "declared": {
        "axes": {
          "fs": 2,
          "net": 1,
          "exec": 1,
          "cred": 2,
          "persist": 3
        },
        "evidence": {
          "fs": "CHANGELOG.md#L30-31 the author states that findings from the skill's own traffic are saved under ~/wstg-evidence/ in the home directory",
          "net": "README.md#L7-9 the author declares only ordinary benign traffic to the application under test, with no payloads or scanners",
          "exec": "README.md#L88-94 the author names local document converters such as pandoc or python-docx for the Word report",
          "cred": "README.md#L33-37 the author declares a plain-text file with test credentials in the working directory",
          "persist": "README.md#L39-42 the author declares that the skill may create a test account in the target application once the statement of work allows it and the tester confirms, which is a new user on the target"
        }
      },
      "static": {
        "level": 3,
        "axes": {
          "fs": 2,
          "net": 1,
          "exec": 2,
          "cred": 2,
          "persist": 3,
          "hitl": null
        },
        "evidence": {
          "fs": "SKILL.md#L146-148 the agent writes the requests and responses it sent into ~/wstg-evidence/ in the home directory, outside the working directory",
          "net": "SKILL.md#L140-142 the agent itself sends benign requests such as fingerprinting, header checks and forced-browsing checks to the target confirmed at the authorization gate",
          "exec": "SKILL.md#L174-176 report conversion is left to whatever document tooling the environment offers, with no fixed list of programs",
          "cred": "SKILL.md#L43-52 the agent reads a plain-text file with several test accounts and their passwords from the working directory",
          "persist": "SKILL.md#L233-240 after the statement of work and a real-time go-ahead the agent may create a user account in the target application, which is a new user on the target and therefore level 3",
          "hitl": "no evidence: no allowed-tools, settings or auto-mode instructions were found, but the search patterns for approvals match one line in SKILL.md, so a zero cannot be written"
        },
        "unknown": [
          "hitl"
        ]
      },
      "min_config": {
        "status": "derived",
        "claude_code": "permissions.allow: [Read, Grep]; keep Bash, Write and WebFetch on ask, and keep test-credentials.txt and ~/wstg-evidence/ out of synced or shared folders",
        "note": "derived from the code, not tested in the lab"
      },
      "override": null,
      "reviews": []
    },
    "status": {
      "tier": "listed",
      "last_checked": "2026-10-21",
      "next_check": "2027-01-19",
      "freshness": "fresh",
      "superseded": false,
      "superseded_by": null,
      "added": "2026-10-21",
      "added_by": "scout"
    },
    "evidence": {
      "runs": [],
      "badge": "/badge/accessitgroup-webapp-testing-checklist.svg"
    },
    "changes": []
  },
  "profile": {
    "schema_version": "0.1",
    "entry": "accessitgroup-webapp-testing-checklist",
    "draft": "review",
    "commit": "d79e59434bb7d3ddc61629e3cced9b55ffbaf39b",
    "read_on": "2026-10-25",
    "check": {
      "date": "2026-10-25",
      "facts": 52,
      "confirmed": 52,
      "verified": 47
    },
    "overview": {
      "text": "A skill that walks a web application penetration test through the OWASP Web Security Testing Guide (WSTG) as a structured checklist and produces WSTG-numbered findings. It aids a human-led engagement: it may send benign traffic, while attack testing stays with the tester's own tooling.",
      "ev": "SKILL.md#L3 frontmatter description"
    },
    "purpose": [
      {
        "text": "Structures an authorized web application penetration test around the OWASP WSTG methodology and tracks checklist coverage.",
        "ev": "SKILL.md#L8-9 opening description"
      },
      {
        "text": "Turns tester-supplied evidence into a findings report with WSTG-numbered IDs.",
        "ev": "README.md#L3-5 README description"
      },
      {
        "text": "Asks a diagnostic question per WSTG test and interprets the evidence the tester hands over, including raw Burp/ZAP captures.",
        "ev": "README.md#L11-12 role of the skill in backseat mode"
      }
    ],
    "use_cases": [
      {
        "text": "Plan, scope or track a web application pentest against the WSTG checklist.",
        "task": "web-api-testing",
        "ev": "SKILL.md#L3 trigger conditions in frontmatter"
      },
      {
        "text": "Produce a findings report with WSTG IDs in Markdown, Word (.docx) or PDF.",
        "task": "web-api-testing",
        "ev": "SKILL.md#L174-176 report format choice"
      },
      {
        "text": "Assess tester-supplied request/response evidence against a WSTG test's criteria and record the verdict.",
        "task": "finding-validation",
        "ev": "SKILL.md#L87-88 evidence option per test"
      },
      {
        "text": "Walk an API-only target through API Testing plus the API-relevant tests from Authentication, Session, Input Validation and Business Logic.",
        "task": "web-api-testing",
        "ev": "SKILL.md#L71-73 scope intake for API-only apps"
      }
    ],
    "not_for": [
      {
        "text": "The author rules out payloads, injection strings, exploit attempts and scanners; benign traffic is allowed and the tester does the actual security testing.",
        "ev": "README.md#L7-10 backseat-mode statement"
      },
      {
        "text": "Meant as a workflow aid for testers who are already authorized, not as a safeguard against unauthorized use.",
        "ev": "README.md#L47-49 author's scope statement"
      },
      {
        "text": "Covers dynamic/black-box testing only; the report recommends a separate source code security review when that is in the SOW and source access is given.",
        "ev": "README.md#L75-77 report note on code review"
      }
    ],
    "capabilities": {
      "coverage": "complete",
      "groups": [
        {
          "name": "Step 1 — Authorization gate",
          "does": "Before anything else, has the tester confirm written authorization for the target (signed SOW, pentest agreement or equivalent); stops and explains what is missing.",
          "effects": [],
          "enabled": "default",
          "ev": "SKILL.md#L21-26 Step 1 authorization gate"
        },
        {
          "name": "Test credentials file",
          "does": "Reads the test accounts once from a plain-text file in the working directory (suggested name test-credentials.txt), then refers to them by label only in the session and report.",
          "effects": [
            "reads"
          ],
          "enabled": "default",
          "ev": "SKILL.md#L44-53 credentials file handling"
        },
        {
          "name": "Step 2 — Scope intake",
          "does": "Asks whether the app is server-rendered, API-only or an SPA with a backend API, which decides which of the 12 WSTG categories in references/ apply.",
          "effects": [],
          "enabled": "default",
          "ev": "SKILL.md#L65-74 Step 2 scope intake"
        },
        {
          "name": "Step 3 — Walk the checklist",
          "does": "Loads one references/ category file at a time, states each test ID and what it verifies, and takes evidence or a direct Pass/Fail/N/A verdict from the tester.",
          "effects": [
            "reads"
          ],
          "enabled": "default",
          "ev": "SKILL.md#L81-90 Step 3 checklist walk"
        },
        {
          "name": "Evidence directory convention",
          "does": "Keeps raw request/response captures and screenshots in ~/wstg-evidence/, split into fail-evidence/ and pass-evidence/ with one subfolder per WSTG test ID.",
          "effects": [
            "reads",
            "changes"
          ],
          "enabled": "default",
          "ev": "SKILL.md#L100-106 evidence directory convention"
        },
        {
          "name": "Self-tested findings",
          "does": "Writes the real requests and responses of the skill's own benign checks, such as fingerprinting, header checks and tester-directed forced-browsing/IDOR checks, to evidence.txt.",
          "effects": [
            "reads",
            "changes"
          ],
          "enabled": "default",
          "ev": "SKILL.md#L140-148 self-tested findings"
        },
        {
          "name": "Backseat mode benign traffic",
          "does": "Sends ordinary application traffic itself, such as viewing pages, following links and submitting forms with non-malicious input, when it helps gather checklist context.",
          "effects": [
            "reads",
            "sends-data"
          ],
          "enabled": "default",
          "ev": "SKILL.md#L10-13 backseat mode traffic"
        },
        {
          "name": "Account creation (gated)",
          "does": "Creates a test account in the target application only after the tester confirms the SOW allows it and gives a real-time go-ahead for that account.",
          "effects": [
            "changes"
          ],
          "enabled": "optional",
          "ev": "SKILL.md#L233-240 account-creation guardrail"
        },
        {
          "name": "Repeated-attempt tests",
          "does": "Sends repeated requests such as several failed logins for lockout testing after telling the tester the count and target and getting explicit go-ahead each time.",
          "effects": [
            "sends-data"
          ],
          "enabled": "optional",
          "ev": "SKILL.md#L262-268 repeated-attempt guardrail"
        },
        {
          "name": "Step 4 — Report",
          "does": "Asks for Markdown, Word (.docx) and/or PDF and writes the report with whatever document-generation capability the environment has.",
          "effects": [
            "changes"
          ],
          "enabled": "default",
          "ev": "SKILL.md#L172-176 Step 4 report"
        }
      ]
    },
    "architecture": {
      "summary": {
        "text": "The client's model loads each in-scope WSTG category file from references/ one at a time as the walk reaches it, instead of all 12 up front.",
        "ev": "SKILL.md#L81-82 per-category loading of references"
      },
      "runs": {
        "where": "in-client",
        "text": "Runs as a Claude Code skill whose instructions the client's model follows.",
        "ev": "README.md#L3 skill description"
      },
      "modes": [],
      "parts": [
        {
          "name": "SKILL.md",
          "zone": "client",
          "does": "Skill manifest with frontmatter name webapp-testing-checklist and a description of the WSTG checklist walk, findings report and backseat-mode limits.",
          "ev": "SKILL.md#L1-3 skill manifest frontmatter"
        },
        {
          "name": "references/ category tables",
          "zone": "client",
          "does": "WSTG checklist tables, one file per category, each row a test ID, title and what it verifies; loaded as the walk reaches the category.",
          "ev": "references/00-overview.md#L31-33 structure of category files"
        },
        {
          "name": "test-credentials.txt",
          "zone": "machine",
          "does": "Plain-text file in the working directory with one test account per line: label, role, username, password.",
          "ev": "SKILL.md#L43-48 credentials file format"
        },
        {
          "name": "~/wstg-evidence/",
          "zone": "machine",
          "does": "Evidence directory in the home directory, split into fail-evidence/ and pass-evidence/ with folders named by WSTG test ID (e.g. WSTG-AUTHZ-04).",
          "ev": "SKILL.md#L103-106 evidence folder split"
        },
        {
          "name": "Target web application",
          "zone": "outside",
          "does": "The in-scope hostnames, apps or IP ranges the tester names in Step 1.",
          "ev": "SKILL.md#L29-32 target scope"
        },
        {
          "name": "Tester's own tooling",
          "zone": "machine",
          "does": "Burp Suite, ZAP, curl, browser devtools and similar tools the tester uses for the actual security testing.",
          "ev": "SKILL.md#L15-16 tester's tooling"
        }
      ],
      "listens": [],
      "connections": [
        {
          "to": "Target web application",
          "kind": "target",
          "when": "default",
          "what": "Sends benign requests to the in-scope target, such as fingerprinting, header checks and tester-directed forced-browsing/IDOR checks.",
          "ev": "SKILL.md#L140-142 skill's own benign traffic"
        }
      ],
      "model": {
        "who": "client",
        "text": "The Claude Code client's model reads and follows the skill's instructions.",
        "ev": "README.md#L3 Claude Code skill"
      }
    },
    "needs": [
      {
        "kind": "runtime",
        "text": "Claude Code, with the skill installed from the AITG-hub marketplace or directly.",
        "ev": "README.md#L60 install statement"
      },
      {
        "kind": "authorization",
        "text": "Written authorization to test the specific target, such as a signed SOW or pentest agreement.",
        "ev": "SKILL.md#L26-28 authorization requirement"
      },
      {
        "kind": "authorization",
        "text": "Named engagement, in-scope hostnames/apps/IP ranges, testing window and rules of engagement with points of contact.",
        "ev": "SKILL.md#L29-34 scope and rules of engagement"
      },
      {
        "kind": "credentials",
        "text": "Test accounts in a plain-text file in the working directory, one per line with label, role, username and password.",
        "ev": "SKILL.md#L44-48 credentials file format"
      },
      {
        "kind": "tools",
        "text": "The tester's own testing tools, such as Burp Suite, ZAP, curl or browser devtools, for the actual security testing.",
        "ev": "README.md#L10 tester tooling"
      },
      {
        "kind": "tools",
        "text": "For .docx reports with screenshots, the author reports pandoc or python-docx, where available, as more reliable than OS-builtin converters.",
        "ev": "README.md#L93-94 .docx toolchain note"
      },
      {
        "kind": "tools",
        "text": "Screenshots of self-tested findings need a visual or browser-automation capability in the environment, not just a CLI HTTP client.",
        "ev": "SKILL.md#L153-155 screenshot condition"
      }
    ],
    "installer": [
      {
        "text": "Adds the AITG-hub marketplace from the GitHub repository AccessITGroup/claude-plugins, then installs webapp-testing-checklist@AITG-hub; the marketplace repository is separate from this one.",
        "ev": "README.md#L62-65 install commands"
      },
      {
        "text": "Versions follow the webapp-testing-checklist entry in the AITG-hub marketplace; CHANGELOG.md lists 0.7.0 as the latest.",
        "ev": "CHANGELOG.md#L3-6 version mapping"
      }
    ],
    "limits": [
      {
        "text": "The authorization gate is a prompt the model follows and cannot verify anything; it relies on the tester answering honestly.",
        "ev": "README.md#L44-46 author warning on the gate"
      },
      {
        "text": "The author notes that a fork can strip the guardrails out entirely.",
        "ev": "README.md#L46-47 author warning on forks"
      },
      {
        "text": "test-credentials.txt holds live secrets in plain text in the working directory; the skill reminds the tester to .gitignore it and delete it after the engagement.",
        "ev": "SKILL.md#L54-56 credentials file reminder"
      },
      {
        "text": "~/wstg-evidence/ in the home directory can accumulate captured HTTP traffic, cookies, session tokens and client-identifying data; the skill prompts the tester to delete or archive it after the report.",
        "ev": "SKILL.md#L206-210 evidence cleanup reminder"
      },
      {
        "text": "Target page bodies, headers and pasted captures enter the model's context; the skill tells the model to treat instructions inside them as data and not act on them.",
        "ev": "SKILL.md#L214-220 prompt-injection guardrail"
      },
      {
        "text": "The guardrail eval cases in evals/ were written against the documented schema and have not been run end to end.",
        "ev": "evals/README.md#L21-23 author note on eval status"
      },
      {
        "text": "Running the eval suite with claude plugin eval requires early access on the account or organization.",
        "ev": "evals/README.md#L20-21 eval prerequisite"
      },
      {
        "text": "A clean run is not a certification; WSTG is not exhaustive and the references/ summaries are shorter than the full WSTG guidance.",
        "ev": "README.md#L81-83 limitations"
      },
      {
        "text": "The client's model reads the credentials file itself, so test usernames and passwords enter its context; the skill tells it not to repeat them in the conversation or report.",
        "ev": "SKILL.md#L52-54 model reads the credentials file directly"
      },
      {
        "text": "The skill tells the model to decline destructive, high-volume or DoS-style traffic, regardless of what the stated rules of engagement say.",
        "ev": "SKILL.md#L241-246 destructive-traffic guardrail"
      },
      {
        "text": "The skill tells the model to stop and reconfirm scope before touching a host, port or path that was not confirmed at Step 1.",
        "ev": "SKILL.md#L247-250 scope-drift guardrail"
      },
      {
        "text": "The skill tells the model never to run exploit code, PoC scripts or third-party attack tooling, even when the tester supplies it, and to hand that back to the tester.",
        "ev": "SKILL.md#L257-261 exploit-execution guardrail"
      }
    ],
    "not_found": [
      {
        "field": "maturity",
        "searched": "README.md, SKILL.md, CHANGELOG.md for preview/alpha/beta/stable/experimental/deprecated; only version numbers 0.1.0 to 0.7.0"
      },
      {
        "field": "capability_count",
        "searched": "README.md, SKILL.md: author states 12 WSTG categories, a unit outside tools/skills/commands/steps/agents/programs"
      },
      {
        "field": "run_mode",
        "searched": "README.md, SKILL.md for alternative modes, flags or environment variables"
      },
      {
        "field": "listen",
        "searched": "all 54 downloaded files; repository holds markdown only, no code, host, port or bind settings"
      },
      {
        "field": "autonomy",
        "searched": "entry type is skill, so the agent autonomy field does not apply"
      },
      {
        "field": "declared reach (allowed-tools)",
        "searched": "SKILL.md frontmatter L1-L4: name and description only"
      },
      {
        "field": "manifest plugin.json",
        "searched": "files.json: no plugin.json or .claude-plugin/ in this repository; marketplace manifest lives in AccessITGroup/claude-plugins (not downloaded)"
      }
    ]
  },
  "verdict": null,
  "runs": []
}