github
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious code, obfuscation, or unauthorized data exfiltration patterns were identified. The skill adheres to its stated purpose and utilizes official tools.
- [COMMAND_EXECUTION]: The skill utilizes the official GitHub CLI (gh) for repository management and Actions monitoring. This is a trusted tool and the intended mechanism for the skill's functionality.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it reads and processes external data from pull requests and issues. Ingestion points: Reading PR bodies (e.g., via
gh pr create --fill) and triaging issues. Boundary markers: None identified in the skill instructions. Capability inventory: The skill can modify code, merge pull requests, and manage GitHub Actions workflows. Sanitization: No explicit sanitization or input validation for external data is defined.
Audit Metadata