overhaul
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify external codebases, creating a vulnerability surface where malicious instructions embedded in a repository could influence the agent.
- Ingestion points: The skill ingests "a whole repository, platform, major subsystem, or long-running improvement program" as described in SKILL.md.
- Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded instructions within the processed files.
- Capability inventory: The workflow involves executing tests, builds, lints, and deployment checks, which provides a path for code execution based on repository content.
- Sanitization: The skill lacks instructions for sanitizing or validating external repository content before processing or executing related commands.
Audit Metadata