linkfox-zhihuiya-fulltext-image

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/zhihuiya_fulltext_image.py to interact with the patent data service.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to https://tool-gateway.linkfox.com/zhihuiya/fulltextImage and https://skill-api.linkfox.com/api/v1/public/feedback. These endpoints are owned by the vendor and are necessary for the skill's primary function.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests data from external API responses. Ingestion points: Data from the Zhihuiya API is processed in scripts/zhihuiya_fulltext_image.py. Boundary markers: The SKILL.md file provides clear instructions to format output as structured tables and explicitly forbids the fabrication of results. Capability inventory: The skill uses Python scripts to perform network operations. Sanitization: Parameters are validated for presence and length, and API responses are parsed as structured JSON.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 05:32 AM