pr-name
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional text for the AI agent. It does not include tools, scripts, or any form of executable content.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external pull request data (titles and diffs) which could contain adversarial instructions.
- Ingestion points: PR titles and diffs as specified in the instructions.
- Boundary markers: None specified to separate data from instructions.
- Capability inventory: None; the skill lacks access to the file system, network, or external tools.
- Sanitization: No filtering or validation of input is present. Note: The lack of capabilities renders this surface low-risk.
Audit Metadata