photo-restoration
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions are clear, task-oriented, and do not attempt to override the AI's safety guidelines or extract system prompts.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths (e.g., .ssh, .aws), or unauthorized network operations were detected.
- [Obfuscation] (SAFE): The content is entirely plain text with no use of Base64, zero-width characters, or homoglyphs to hide malicious commands.
- [External Downloads & Remote Code Execution] (SAFE): The skill does not install third-party packages (npm/pip) or execute remote scripts via curl/wget.
- [Indirect Prompt Injection] (SAFE): While the skill ingests user images, it does so through a standard image generation tool's reference parameter without any high-privilege capabilities that could be exploited via image-based instructions.
Audit Metadata