get-pr-comments
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external, user-controllable sources (pull request comments) to generate feedback summaries and action lists.
- Ingestion points: Comments are retrieved from active pull requests as described in the
SKILL.mdworkflow. - Boundary markers: The instructions do not define delimiters or provide specific prompts to the agent to ignore instructions embedded within the fetched comments.
- Capability inventory: The workflow implies capabilities to interact with Git/GitHub tools to resolve pull requests and fetch discussion data.
- Sanitization: No evidence of sanitization, filtering, or validation of the retrieved PR comment content is present in the skill definition.
- [NO_CODE]: The skill consists entirely of descriptive workflow documentation and metadata. No executable scripts or package manifests are provided in the source.
Audit Metadata