product-review-analysis
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of descriptive text and instructions for the agent to follow. No malicious instructions, such as prompt injection or safety bypasses, were detected.
- [EXTERNAL_DOWNLOADS]: The documentation mentions an installation command using
npxand links to GitHub repositories. These resources belong to the vendor 'nexscope-ai' and are used for skill distribution, which is a standard practice. - [DATA_EXFILTRATION]: No network operations, sensitive file path access, or credential harvesting patterns were found in the skill content.
- [INDIRECT_PROMPT_INJECTION]: Although the skill processes untrusted external data (product reviews), it lacks the capabilities (like file writing or command execution) that would make it vulnerable to exploitation through this vector.
Audit Metadata