Agent supply-chain scan
2 tools. Compare how each tool runs, what it needs, where it sends data, what it can change and what its code can touch. Feed: /tasks/agent-supply-chain-scan/feed.xml
| Tool | Runs and needsWhere the tool runs and what must be in place before it works. | Sends data toOutside parties the tool contacts, read from the code and the documentation. Other connections are not ruled out. | Can change thingsWhether the tool's functions only read, or also create, change or delete things, run commands, or send data out. | How to run itThe run advice where we have read the tool under the verdict rule, else what the code shows; below it, whether it has run in our lab. |
|---|---|---|---|---|
| Cisco MCP Scanner PluginDraft · awaiting review Claude Code plugin that scans MCP servers and tools for prompt injection, tool poisoning and other risks via the Cisco MCP scanner. Plugin · cisco-ai-defense, pushed 2026-10-16 | Inside your AI client Works with: Claude Code Needs: Claude Code, which loads the plugin from its folder with --plugin-dir; The cisco-ai-mcp-scanner Python package, installed separately from the plugin; +5 more | Remote MCP server (named URL), Remote servers listed in client configs, LLM provider via LiteLLM, Cisco AI Defense inspect API, Package registries of launched servers, mcp.deepwiki.com, VirusTotal | changes, runs commands, sends data out | Code shows: reads credential stores · talks to any host · runs shell commands or eval · +2 more Ran once, 2026-11-07: did more than it said |
| Trail of Bits Agentic Actions AuditorDraft · awaiting review Claude Code plugin that statically audits GitHub Actions workflows which invoke AI coding agents for injection and permission flaws. Plugin · trailofbits, pushed 2026-10-15 | Inside your AI client Works with: Claude Code, Codex Needs: Claude Code with the trailofbits/skills plugin marketplace added; the root README also documents Codex; The GitHub CLI (gh) for remote analysis mode and remote cross-file fetches; +2 more | GitHub API (named repository), GitHub API (referenced repositories) | runs commands | Code shows: runs shell commands or eval · has broad pre-approvals Not run yet |