cis-controls
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or obfuscation techniques were detected. The skill consists entirely of markdown-based reference material.
- [DATA_EXPOSURE]: No sensitive file paths, hardcoded credentials, or unauthorized network communication patterns were identified.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote code execution or download any untrusted dependencies. All referenced tools and URLs point to well-known, authoritative cybersecurity resources (e.g., Center for Internet Security).
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests user input for security assessments, it lacks dangerous capabilities such as file system writes or shell command execution, rendering the surface area for exploitation safe.
Audit Metadata