web-search

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No prompt injection, jailbreak attempts, or safety bypass instructions were detected in the skill body or metadata.
  • [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were identified. The mention of TAVILY_API_KEY and EXA_API_KEY refers to necessary user configuration and does not involve hardcoded secrets.
  • [REMOTE_CODE_EXECUTION]: The skill does not include any scripts, external package installations, or remote code download patterns.
  • [SAFE]: The skill describes a standard search tool interface and follows best practices for tool documentation without introducing security risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:19 PM