linkfox-google-patent-search

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local Python scripts (google_patent_search.py and onboarding.py) to perform its functions. These scripts are invoked via the shell, receiving parameters as JSON strings.
  • [EXTERNAL_DOWNLOADS]: The skill's scripts communicate with tool-gateway.linkfox.com, api.linkfox.com, and agent-api.linkfox.com. These are legitimate endpoints managed by the vendor (linkfox-ai) for patent data retrieval and account services.
  • [PERSISTENCE_MECHANISMS]: The skill provides explicit instructions for users to save their API keys in shell profiles (e.g., .bashrc, .zshrc) or Windows environment variables. This is a transparent configuration step for the user's environment and is standard practice for CLI-based authentication.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external patent data from Google Patents. While this presents an ingestion surface for indirect prompt injection, the skill includes specific display rules and instructions for the agent to format the output as a table, which helps mitigate the risk of the agent misinterpreting embedded data as commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 03:04 PM
Security Audit — agent-trust-hub — linkfox-google-patent-search