github
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses the official GitHub CLI (
gh) to interact with a well-known service (GitHub) for legitimate development tasks. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves content from external sources (GitHub issues and pull requests) which could contain adversarial instructions. This is a common characteristic of skills that process external text data.
- Ingestion points: Data is ingested via commands like
gh pr viewandgh issue listinSKILL.md. - Boundary markers: None identified.
- Capability inventory: The skill can perform actions like
gh pr merge,gh issue create, andgh issue close. - Sanitization: No specific sanitization of retrieved issue/PR text is implemented in the templates.
Audit Metadata