gsp-screenshot-critic
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, such as prompt injection, obfuscation, or unauthorized network activity, were identified in the skill instructions.
- [SAFE]: The skill uses local file paths for checklists and reporting, which is a standard organizational practice and does not involve external data exfiltration.
- [SAFE]: While the skill processes untrusted visual input (screenshots), which is a surface for indirect prompt injection, it lacks dangerous capabilities like remote code execution or credential access that would make this surface critical.
Audit Metadata