web-research

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill appropriately leverages the Task tool to delegate web research to a specific subagent (gemini-search:gemini-search), which is a standard and safe platform capability for modular tasks.\n- [SAFE]: The skill manages its operational data, including cache and analytics, within the /tmp directory. This is standard practice for temporary storage of non-sensitive information.\n- [SAFE]: The instructions provided to the agent include strong best practices for information gathering, such as specific source targeting (e.g., official documentation) and explicit reminders to verify information from reputable sources.\n- [SAFE]: The skill environment configuration relies on standard environment variables for configuration, with no hardcoded credentials or sensitive data exposure identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 12:58 AM
Security Audit — agent-trust-hub — web-research