screenshot-analyze-verification
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of markdown instructions and contains no scripts, binaries, or executable code.
- [Indirect Prompt Injection] (SAFE): The skill is designed to analyze screenshots (untrusted data). However, it lacks any integrated tools or functions (such as shell execution, file system modifications, or outbound network requests) that could be leveraged by a malicious instruction embedded within a processed image.
- [Prompt Injection] (SAFE): No instructions to bypass safety filters or override system prompts were detected within the documentation.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, sensitive file paths, or network exfiltration patterns were identified.
Audit Metadata