visual-keywords
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed strictly of natural language instructions and contains no code, scripts, or system commands.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts visual content as input, which represents an untrusted data surface. While images could contain embedded adversarial text (OCR injection), the skill lacks tools or permissions to perform network requests, file operations, or command execution, neutralizing the risk of a successful exploit.
Audit Metadata