get-pr-comments
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes review and discussion comments from active pull requests, which are untrusted external inputs. This behavior creates a risk where malicious instructions embedded in a PR comment could hijack the agent's summarization task or subsequent actions. \n
- Ingestion points: Review comments and discussion comments retrieved during the pull request resolution workflow in SKILL.md. \n
- Boundary markers: The skill does not define specific delimiters or instructions to treat the fetched comments as data rather than instructions. \n
- Capability inventory: The skill defines a high-level workflow for fetching and grouping data; it does not include explicit script files or command execution instructions. \n
- Sanitization: There is no sanitization or validation logic provided to filter the content of the comments before processing. \n- [NO_CODE]: The skill consists entirely of configuration and instructional markdown without any executable scripts or binary files.
Audit Metadata