skills/firecrawl/cli/firecrawl-search/Gen Agent Trust Hub

firecrawl-search

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute firecrawl and npx firecrawl commands. These operations are limited to the vendor's command-line interface as specified in the allowed-tools configuration.
  • [EXTERNAL_DOWNLOADS]: The skill leverages npx to run the firecrawl package from the npm registry. This allows the agent to use the vendor's official toolset dynamically, which is a standard implementation for this service.
  • [DATA_EXFILTRATION]: The skill performs network operations to conduct web searches and scrape content. This behavior is the primary function of the skill and is directed toward legitimate web resources and the vendor's API.
  • [INDIRECT_PROMPT_INJECTION]: By scraping web content (especially with the --scrape flag), the skill introduces a surface for indirect prompt injection. Malicious instructions embedded in external web pages could be ingested into the agent's context. However, the skill suggests writing large outputs to a local directory (.firecrawl/) to mitigate context window bloat and potential immediate execution risks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 11:27 PM
Security Audit — agent-trust-hub — firecrawl-search