distill-pr
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted external data, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill fetches PR bodies, diffs, commits, review comments, and linked tickets with their comments (SKILL.md, Steps section).
- Boundary markers: The skill implements a 'trust ranking' for sources (e.g., diffs over PR bodies) to prioritize technical data over prose, but lacks explicit prompt boundary markers or instruction-override guards for ingested content.
- Capability inventory: The agent uses environment tools to gather data and produces a structured report based on the analyzed content.
- Sanitization: There is no evidence of sanitization, filtering, or escaping of the external data before it is processed by the agent.
Audit Metadata