why
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by instructing the agent to read commit messages and Pull Request discussions. This data source is controlled by external contributors and could contain embedded instructions designed to influence the agent's analysis or summary.
- Ingestion points: Git commit history and GitHub Pull Request discussions via
ghorgittools. - Boundary markers: None specified; instructions do not include delimiters or specific warnings to ignore instructions embedded within the historical records.
- Capability inventory: The skill leverages file reading and likely utilizes version control tools (git/gh) to access historical data.
- Sanitization: No explicit sanitization or filtering of commit/PR content is defined in the instructions.
Audit Metadata