Skills
skills/skillssh/skills/web-search/Gen Agent Trust Hub

web-search

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool for performing web searches and interacting with AI models. The commands are scoped to the belt utility as defined in the skill's frontmatter.
  • [EXTERNAL_DOWNLOADS]: The instructions reference the installation of the belt CLI through standard package managers (NPM) and point to official documentation and setup scripts hosted on the vendor's GitHub repository.
  • [PROMPT_INJECTION]: Surface for indirect prompt injection detected. Ingestion points: Tavily/Exa outputs in SKILL.md. Boundary markers: Absent. Capability inventory: belt CLI execution in SKILL.md. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 09:08 PM
Security Audit — agent-trust-hub — web-search