Skills
Navigate
skills/hybridlabor-api/aos/firecrawl-search/Gen Agent Trust Hub

firecrawl-search

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites through search results and full-page scraping, which could contain instructions intended to influence agent behavior.
  • Ingestion points: Search results and scraped content returned by the firecrawl tool in SKILL.md.
  • Capability inventory: Shell command execution via Bash(firecrawl *) and Bash(npx firecrawl *).
  • Boundary markers: No specific delimiting instructions or warnings for the agent when processing external content are provided in the skill body.
  • Sanitization: The skill does not perform explicit sanitization of the scraped markdown or JSON data.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of the firecrawl CLI tool to perform web searches and scrapes. The tool usage is constrained to the primary purpose of the skill.
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the firecrawl package from the official npm registry, which is a standard method for utilizing CLI utilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 02:38 PM
Security Audit — agent-trust-hub — firecrawl-search