repository-management
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes functionality to fetch file contents from remote GitHub repositories. This represents a data ingestion point for untrusted content that could potentially harbor instructions intended to influence the agent's behavior.
- Ingestion points: File content retrieval via
gh apiand directory listing commands inSKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" directives are included for the retrieved content.
- Capability inventory: GitHub repository management (creation, forking), branch management, and file system operations.
- Sanitization: The content is retrieved and decoded from the GitHub API without explicit sanitization steps.
Audit Metadata