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