pr
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to generate pull request descriptions, which is a vector for indirect prompt injection.
- Ingestion points: The skill is instructed to review all commits on the branch, conversation history, and 'chalk comments' on tracked issues via the GitHub agent (SKILL.md).
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the ingested data are present.
- Capability inventory: The skill can push branches and create pull requests with titles and descriptions through a delegated GitHub agent (SKILL.md).
- Sanitization: There is no evidence of sanitization or filtering of the content retrieved from commits or issue comments before it is distilled into the PR body.
Audit Metadata