port-features
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and analyze code from external "upstream" repositories, which serves as an ingestion point for potentially untrusted data that could contain hidden instructions or malicious payloads.
- Ingestion points: Local checkouts of upstream codebases, including file contents and git history logs (as specified in Step 1 and Step 2 of the instructions).
- Boundary markers: The instructions do not define clear delimiters or specific warnings for the agent to ignore instructions embedded within the code being ported (e.g., in comments or README files).
- Capability inventory: The agent is authorized to read files, execute shell commands (specifically
git), and write/edit files in the destination project. - Sanitization: There is no mention of sanitizing or validating the content of the upstream code before the agent processes it, which is the standard attack surface for indirect injection in developer-focused skills.
Audit Metadata