firecrawl-api

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Provides examples using standard system tools like curl for network requests and jq for JSON processing.
  • [EXTERNAL_DOWNLOADS]: Interacts with api.firecrawl.dev, which is an established service for web scraping and data extraction.
  • [PROMPT_INJECTION]: This skill facilitates the ingestion of untrusted content from external URLs, creating a surface for indirect prompt injection. 1. Ingestion points: The url parameter in curl commands (SKILL.md). 2. Boundary markers: Not specified in instructions. 3. Capability inventory: Use of curl for data retrieval. 4. Sanitization: No sanitization of output content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 03:28 PM