Firecrawl Web Data API for AI Agents
Pass
Audited by Gen Agent Trust Hub on Jun 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: References the official 'firecrawl' NPM package and fetches documentation from the Firecrawl GitHub repository. These sources are considered legitimate for the provided functionality.
- [PROMPT_INJECTION]: The skill's primary function is scraping web content, which exposes the agent to indirect prompt injection from untrusted external data.
-
- Ingestion points: Web pages and search results processed via the Firecrawl API.
-
- Boundary markers: None specified in the documentation.
-
- Capability inventory: Extraction of markdown and structured JSON for research and retrieval workflows.
-
- Sanitization: No sanitization or filtering logic is defined within the skill itself.
- [SAFE]: The skill metadata includes an unverified 'security_reviewed' status and exaggerated popularity metrics. While these are identified as deceptive data points, they do not introduce executable vulnerabilities or functional hazards.
Audit Metadata