load-pr-context
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external GitHub pull requests, which could be used to influence the agent's behavior via embedded instructions.
- Ingestion points: The skill fetches pull request descriptions, review comments, and file diffs through various GitHub MCP tools (SKILL.md).
- Boundary markers: The implementation instructions do not specify the use of delimiters or 'ignore' instructions when processing the fetched content.
- Capability inventory: The skill is designed to read data and present a summary, but the ingested data enters the agent's context and could affect subsequent operations.
- Sanitization: There is no evidence of sanitization or filtering applied to the external PR content before it is summarized for the agent.
Audit Metadata