skills/beltsh/superpowers/web-search/Gen Agent Trust Hub

web-search

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the 'belt' CLI from the NPM registry and provides documentation links to GitHub-hosted installation guides.
  • [COMMAND_EXECUTION]: Executes bash commands using the 'belt' CLI to perform web searches, login to services, and extract content from remote URLs. These commands are within the scope defined by the 'allowed-tools' restriction.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and processing untrusted data from the internet. While it provides workflow examples using delimiters (e.g., ) to separate data from instructions, the ingestion of external web content presents an inherent surface for indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 12:18 PM