firecrawl

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill requires the installation of the firecrawl-cli@1.4.1 package from the npm registry as described in rules/install.md. While the version is pinned, this is an external dependency from a non-pre-approved source.
  • COMMAND_EXECUTION (LOW): The core functionality of the skill relies on executing shell commands (e.g., firecrawl search, firecrawl scrape). The agent must have permission to execute these commands to function.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection because it ingests untrusted data from the web (scraping, searching, and crawling) and returns it as markdown for the LLM to process.
  • Ingestion points: Scrape, search, and crawl commands in SKILL.md ingest external web content.
  • Boundary markers: Absent. The instructions do not specify how the agent should distinguish between its instructions and the content returned by the tool.
  • Capability inventory: The skill allows for file writing (-o flag), browser automation (firecrawl browser), and autonomous data extraction (firecrawl agent).
  • Sanitization: No explicit sanitization of the scraped markdown content is mentioned in the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 06:23 PM