pr-hygiene
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and summarize external code changes, which introduces a potential attack surface if the code contains embedded instructions.
- Ingestion points: The agent processes repository diffs and branch content (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or warnings to treat the content of the diff as untrusted data rather than instructions.
- Capability inventory: The skill allows the agent to summarize code changes and generate PR documentation.
- Sanitization: There are no instructions to sanitize or filter the content of the diffs before processing.
Audit Metadata