linkfox-zhihuiya-utility-patent-image-search

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [PERSISTENCE_MECHANISMS]: The onboarding documentation in onboarding.md instructs users to persist API keys by adding export commands to shell profiles like .bashrc or .zshrc. This is a standard and transparent procedure for configuring environment variables required for tool authentication.
  • [DATA_EXPOSURE]: The skill manages user credentials via environment variables and transmits onboarding data, including phone numbers, to vendor-controlled endpoints at *.linkfox.com in onboarding.py. This represents standard operational behavior for the service's authentication flow.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes patent metadata from the Zhihuiya API. Evidence Chain: 1. Ingestion points: zhihuiya_patent_image_search.py reads data from the patent search API response; 2. Boundary markers: Absent; 3. Capability inventory: Python script execution and local file writing in the linkfox/ directory; 4. Sanitization: Absent. The risk is classified as low due to the specialized nature of the retrieved content and the skill's specific retrieval context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:03 AM
Security Audit — agent-trust-hub — linkfox-zhihuiya-utility-patent-image-search