Skills
skills/gooseworks-ai/goose-skills/web-search-valyu/Gen Agent Trust Hub

web-search-valyu

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (python3 and curl) for essential setup and API communication. python3 is used to parse a local JSON configuration file (~/.gooseworks/credentials.json), while curl manages requests to the vendor's official API endpoints at api.gooseworks.ai.
  • [PROMPT_INJECTION]: The skill acts as a research tool that processes external web content and user-supplied queries, representing a surface for indirect prompt injection.
  • Ingestion points: The query, urls, and instruction parameters in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are used to isolate ingested data from agent instructions.
  • Capability inventory: The skill has network communication capabilities via curl.
  • Sanitization: No explicit content sanitization is described; the skill relies on the backend API and the model's inherent guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 02:14 PM
Security Audit — agent-trust-hub — web-search-valyu