ecommerce-ruiguan-copyright-detection

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The Python scripts (ruiguan_copyright_detection.py and upload_image.py) make network requests to Nexscope API endpoints (via NEXSCOPE_PROXY_BASE and specific feedback URLs) to perform copyright analysis and asset uploads. These operations are required for the skill's primary functionality and target vendor-controlled domains.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and displays information returned from an external API (such as rights owner details and similarity scores). This creates a vulnerability surface where the agent could potentially be influenced by instructions embedded in the API response data.
  • Ingestion points: The call_api function in scripts/ruiguan_copyright_detection.py receives JSON data from a remote endpoint.
  • Boundary markers: The skill documentation provides display rules but does not implement specific delimiters or 'ignore' instructions for the ingested data.
  • Capability inventory: The skill includes network access and the ability to write files to the local filesystem for caching and session management.
  • Sanitization: The scripts do not perform specific sanitization or filtering of the API response content beyond standard JSON parsing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 07:19 AM
Security Audit — agent-trust-hub — ecommerce-ruiguan-copyright-detection