Skip to content

Rule reference

agentgate scan runs seven rules, one per finding category. Each rule can inspect up to four surfaces:

  • config — MCP client config entries (static, always runs).
  • tool — a single tool’s name/description/input schema (--live or lockfile audit).
  • toolset — a server’s whole tool surface at once.
  • source — files in a repo target (agentgate scan path/to/repo).
Rule Category Detects
AG-TP-001 tool-poisoning Hidden Unicode and prompt-injection patterns in tool descriptions
AG-CL-001 credential-leak Hardcoded secrets in configs; tools soliciting credentials
AG-OP-001 overprivileged Dangerous capability combos; overly broad filesystem grants
AG-AM-001 auth-missing Remote servers without auth or over plain HTTP
AG-SS-001 ssrf Cloud-metadata endpoints; unrestricted URL-fetching tools
AG-RC-001 rce-vectors Shell-wrapped launches, curl|sh, arbitrary code-execution tools
AG-SC-001 supply-chain Unpinned npx pkg@latest launches, unpinned docker images

Severities: critical > high > medium > low > info. Gate on them with agentgate scan --fail-on <severity> or agentgate ci.