firecrawl-crawl

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the firecrawl CLI tool to execute crawling operations (e.g., firecrawl crawl "<url>"). This is the primary functionality of the skill and involves standard parameters for depth, limits, and output redirection.
  • [PROMPT_INJECTION]: As a data extraction tool, this skill possesses an inherent surface for indirect prompt injection by ingesting untrusted content from external websites.
  • Ingestion points: External web content is retrieved via the firecrawl crawl command from user-provided or discovered URLs.
  • Boundary markers: The skill does not define specific delimiters or instructions to treat the crawled output as untrusted data.
  • Capability inventory: The skill allows writing the ingested data to the local filesystem using the -o or --output flag (e.g., .firecrawl/crawl.json).
  • Sanitization: No explicit sanitization or filtering of the crawled content is described within the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 11:49 PM
Security Audit — agent-trust-hub — firecrawl-crawl