agent-security-audit
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill's instructions are consistent with its stated purpose of security auditing. It references recognized security standards (OWASP LLM Top 10) and follows a logical methodology for risk assessment.
- [NO_CODE]: The skill is composed exclusively of markdown documentation. It does not define any tools, scripts, or automated commands, which prevents execution-based attacks.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external agent configurations, creating a surface for processing untrusted data. 1. Ingestion points: Review of CLAUDE.md files, MCP configurations, and agent orchestration code (SKILL.md). 2. Boundary markers: Not present in the audit instructions. 3. Capability inventory: No tools or shell commands are defined in this skill. 4. Sanitization: The skill instructions focus on human or agent-led analysis rather than automated data processing.
Audit Metadata