linkfox-ruiguan-gun-parts-search

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to fetch additional onboarding resources from the vendor's file server at agent-files.linkfox.com if required for setup.
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (upload_image.py and ruiguan_image_compliance_search.py) to facilitate image uploads and query the Ruiguan detection API.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes and displays product titles and descriptions (pdTitle, pdTitleCHNCensored) retrieved from the external compliance API.
  • Ingestion points: Product metadata and titles returned from the Ruiguan API in the search script.
  • Boundary markers: Not explicitly defined in the display instructions for API results.
  • Capability inventory: The skill can perform network operations and local file writes for session logging.
  • Sanitization: Results are presented in a structured table for user validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 08:08 AM