agency-security-architect
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions and configuration are strictly focused on defensive security practices and do not exhibit malicious behavior or attempt to bypass system constraints.
- [EXTERNAL_DOWNLOADS]: The CI/CD pipeline examples provided in the documentation reference official GitHub Actions from well-known security providers, including Semgrep, Aqua Security (Trivy), and Gitleaks. These are standard industry tools for static analysis and secret detection.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes technical documentation and source code (Ingestion points: system architecture, config files). While boundary markers are not explicitly defined in the instructions, the agent's capability inventory is limited to analysis and it lacks autonomous execution tools. The skill prioritizes identifying risks and recommending sanitization for the target systems it reviews.
Audit Metadata