photo-restoration
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill instructions or scripts. All functionality aligns with the stated purpose of providing photo restoration services.
- [COMMAND_EXECUTION]: Documentation includes curl command examples for interacting with the eachlabs API. These are illustrative for developers and use environment variables for credential management, which is a safe practice.
- [EXTERNAL_DOWNLOADS]: The skill references image processing via external URLs and output storage on vendor-controlled domains (storage.eachlabs.ai), which is expected behavior for an image processing skill.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external user content (images and text) which constitutes an indirect injection surface. However, this is inherent to the AI restoration task and is mitigated by vendor-side safety policies.
Audit Metadata