gcpd
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow external instructions from other files, which is a potential injection surface.\n
- Ingestion points: The agent is directed to locate and read the full contents of
git-commit-push-deploy/SKILL.mdand the repository's deployment settings (e.g.,AGENTS.md).\n - Boundary markers: The instructions do not define boundary markers or clear separators when reading the external skill or configuration files.\n
- Capability inventory: The skill itself does not possess direct tool capabilities, instead delegating all Git and deployment operations to the canonical skill it references.\n
- Sanitization: No explicit sanitization or validation logic is defined to check the content of the external files being read.\n- [NO_CODE]: The skill consists exclusively of markdown instructions and configuration metadata, with no accompanying scripts or binaries.
Audit Metadata