custom-builtin-functions
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): The instructions are strictly technical and do not attempt to override agent behavior or bypass safety filters.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or suspicious network calls were found.
- [Unverifiable Dependencies] (SAFE): The Go code imports standard Open Policy Agent (OPA) libraries which are trusted for this context. No remote script execution patterns (e.g., curl | bash) are present.
- [Indirect Prompt Injection] (SAFE): This skill acts as a code template; it does not ingest untrusted external data during its operation that could influence agent logic.
Audit Metadata