visual-audit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists of a set of prompts and constraints for visual analysis and does not contain any malicious instructions, obfuscation, or sensitive data access. \n- [NO_CODE]: The skill does not include any Python or Node.js scripts, nor does it attempt to download or execute external code. \n- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted external data (images/URLs) but presents minimal risk due to a complete lack of system-level capabilities. \n
- Ingestion points: Images or URLs provided via the
/visual-auditcommand as described inSKILL.md. \n - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts in the visual content. \n
- Capability inventory: No tools for network access, file writing, or command execution are requested or used by this skill. \n
- Sanitization: None.
Audit Metadata