web-search

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Python and shell commands to manage local credentials and execute API requests.
  • Reads API keys and base URLs from ~/.gooseworks/credentials.json using python3 -c with json.load.
  • Uses curl to make network requests to the vendor's API proxy ($GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run).
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to various search providers (Tavily, Exa, Andi, Linkup, Valyu, and SearchAPI) through the Gooseworks proxy.
  • These requests are used for searching the web, social platforms (YouTube, TikTok, Instagram), and marketplaces (Amazon, eBay, Walmart) to retrieve information as requested by the user.
  • [CREDENTIALS_UNSAFE]: While the skill accesses credentials from the filesystem, it does so using a standard local configuration path (~/.gooseworks/credentials.json) rather than hardcoding sensitive tokens in the skill itself. This is considered a safe practice for agentic tools requiring authentication.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 02:14 PM
Security Audit — agent-trust-hub — web-search