get-pr-comments
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process feedback from pull request comments, which are external, untrusted data sources. This creates a surface for indirect prompt injection if the comments contain malicious instructions intended to manipulate the agent's behavior during summarization.
- Ingestion points: Pull request review comments and discussion comments fetched in step 2 of the workflow.
- Boundary markers: No explicit instructions for delimiters or guardrails to separate untrusted comment data from agent instructions are provided in the workflow.
- Capability inventory: The skill description implies the use of external tools to resolve branches and fetch PR data, though no specific code or scripts are included within this skill definition.
- Sanitization: No methods for sanitizing, filtering, or validating the content of the comments are mentioned.
Audit Metadata