search
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script located at
./scripts/search.shto process search queries. The provided examples demonstrate secure practices by wrapping JSON payloads in single quotes to prevent argument injection. - [EXTERNAL_DOWNLOADS]: The skill makes network requests to
api.tavily.com. This is a well-known service specifically designed for LLM-optimized web searching. - [CREDENTIALS_UNSAFE]: The documentation mentions storing API keys in
~/.claude/settings.jsonand checking for tokens in~/.mcp-auth/. These are standard configuration paths for managing service credentials and do not represent a security risk. - [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were detected. The skill's behavior matches its stated purpose of providing web search capabilities.
Audit Metadata