firecrawl-crawl

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute firecrawl and npx firecrawl-cli. These commands are used to perform website crawling, check job status, and manage credit usage.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to run firecrawl-cli. This involves fetching the package from the npm registry. The package is associated with the vendor 'firecrawl'.
  • [INDIRECT_PROMPT_INJECTION]: This skill has an attack surface for indirect prompt injection as it ingests content from external websites.
  • Ingestion points: External website content accessed via the <url> parameter in SKILL.md.
  • Boundary markers: The extracted data is stored in a structured JSON file at .firecrawl/crawl.json.
  • Capability inventory: The skill uses the Bash tool to execute CLI commands.
  • Sanitization: The skill relies on the CLI's internal processing and the structured nature of JSON output to mitigate instruction leakage into the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 03:55 AM