web-search

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web content from search and extraction results, which serves as an attack surface where hidden instructions could influence the agent's logic.- [EXTERNAL_DOWNLOADS]: The documentation references an external CLI tool installation ('belt-sh/cli') and links to installation scripts hosted on GitHub.- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute 'belt' CLI commands for interacting with remote search and extraction APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:30 AM
Security Audit — agent-trust-hub — web-search