pr-summary
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to create pull request summaries.
- Ingestion points: Pull request diffs and issue specifications as defined in SKILL.md.
- Boundary markers: No delimiters or boundary markers are instructed to separate external data from agent instructions.
- Capability inventory: No high-risk capabilities like network access, command execution, or sensitive file writing were identified.
- Sanitization: No instructions for sanitizing or escaping the external content were found.
Audit Metadata