code-documentation
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill handles untrusted data by documenting external codebases and API definitions.\n
- Ingestion points: External source code and API specifications.\n
- Boundary markers: Absent in provided templates.\n
- Capability inventory: None (the skill consists of static text templates).\n
- Sanitization: Absent.\n- [Prompt Injection] (SAFE): No instructions to override agent behavior or bypass safety filters were detected.\n- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive file access patterns were identified. Mentions of secrets in templates use generic placeholders.\n- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No remote script downloads or runtime execution of external packages were found.
Audit Metadata