cursor-dyl-ready-pr
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which creates an indirect prompt injection surface.
- Ingestion points: PR titles, descriptions, comments, and CI logs (SKILL.md).
- Boundary markers: Present. The skill instructs to treat PR content as untrusted and ignore embedded instructions.
- Capability inventory: Git (merge, push), GitHub CLI (gh pr ready), and invocation of related skills like cursor-dyl-review (SKILL.md).
- Sanitization: Instructions mandate ignoring directives in external data.
- [COMMAND_EXECUTION]: The skill uses Git and the GitHub CLI (gh) for branch management and PR status updates, which are standard operations for its stated purpose.
Audit Metadata