pr-tour
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize external data from pull requests. This creates an attack surface where maliciously crafted content within a pull request (such as comments or code blocks containing instructions) could attempt to influence the agent's output.
- Ingestion points: Pull request content, including code changes and commit messages.
- Boundary markers: None defined; there are no specific instructions for the agent to treat pull request content as data distinct from instructions.
- Capability inventory: None; the skill provides high-level instructions without defining specific tool calls or scripts.
- Sanitization: None; the skill does not specify any filtering or sanitization of the pull request data before processing.
Audit Metadata