visual-keywords
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [No Code] (SAFE): The skill is composed exclusively of markdown instructions and examples. No scripts (Python, JS, etc.) or binary files are present.
- [Data Exposure & Exfiltration] (SAFE): There are no references to sensitive file paths, environment variables, or hardcoded secrets.
- [Indirect Prompt Injection] (SAFE): The skill processes untrusted visual data. Evidence: 1. Ingestion point: User-provided visual content via prompt. 2. Boundary markers: None. 3. Capability inventory: Limited to text generation; no subprocess, network, or file-write capabilities detected. 4. Sanitization: None. Due to the lack of dangerous capabilities, this surface presents no significant security risk.
Audit Metadata