Skills
skills/inference-sh/skills/web-search/Gen Agent Trust Hub

web-search

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides links to installation guides and additional tools on the official 'inference-sh' GitHub organization. These are standard resources for tool setup.\n- [COMMAND_EXECUTION]: Operational examples utilize the 'infsh' CLI tool for interacting with search APIs. This usage is restricted to the specific vendor tool.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from the web (via Tavily and Exa) and recommends processing it with LLMs. This is an indirect prompt injection surface.\n
  • Ingestion points: tavily/extract and exa/extract in SKILL.md.\n
  • Boundary markers: Absent in examples.\n
  • Capability inventory: infsh CLI.\n
  • Sanitization: None mentioned.\n
  • This behavior is the primary intended function for research tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 07:02 PM