security-auditor
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of descriptive text and instructions to define an expert security auditor persona. No executable code, scripts, or system commands were found.
- [INDIRECT_PROMPT_INJECTION]: The skill involves auditing external assets (code, architecture, CI/CD), which creates a standard ingestion surface for indirect prompt injection.
- Ingestion points: Source code, architecture documents, threat models, and vulnerability reports described in SKILL.md.
- Boundary markers: None explicitly defined to delimit audited data from system instructions.
- Capability inventory: Mentions the use of SAST/DAST tools and CI/CD integrations, though these are not implemented within the skill itself.
- Sanitization: No instructions provided for escaping or validating external input before processing.
Audit Metadata