web-search-andi

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to manage authentication and interact with the search API. Evidence: Uses python3 to parse the API key from ~/.gooseworks/credentials.json. Evidence: Employs curl to send POST requests for searching and retrieving endpoint details.
  • [EXTERNAL_DOWNLOADS]: The skill makes network calls to retrieve search results and metadata from the vendor's infrastructure. Evidence: Directs requests to api.gooseworks.ai, which is the official domain for the skill vendor.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it retrieves and processes content from the open web. Ingestion points: Results from the search query endpoint in SKILL.md. Boundary markers: Not specified. Capability inventory: Shell access through curl and python3. Sanitization: No explicit validation or filtering of search results is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 02:15 PM
Security Audit — agent-trust-hub — web-search-andi