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

web-search

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation provides command patterns for using the belt CLI tool to execute search and content extraction applications.
  • [EXTERNAL_DOWNLOADS]: The instructions include links to installation scripts and references to related skill modules hosted within the official inference-sh GitHub repository.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by facilitating the retrieval of web data for LLM analysis. The provided workflow examples follow safety protocols by using explicit XML-style tags to delimit external content and prevent the agent from misinterpreting it as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:48 AM
Security Audit — agent-trust-hub — web-search