github
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions were found that attempt to override agent behavior or bypass safety constraints.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or unauthorized network requests were detected; the skill uses the standard GitHub CLI tool.
- [Unverifiable Dependencies] (SAFE): No external package installations or remote script executions are present.
- [Indirect Prompt Injection] (SAFE): The skill enables the agent to read external data from GitHub. While this is an attack surface for indirect injection, the skill itself is purely instructional and lacks automated processing logic. Evidence: 1. Ingestion: GitHub API/CLI output. 2. Boundary markers: Absent. 3. Capability: CLI execution. 4. Sanitization: N/A.
Audit Metadata