Call
on npm:firecrawl-mcp@3.20.1
Severity
1 finding on this tool
- mediumindirect injectionf-r6-call
Tool `Call` fetches external web content -- indirect-injection surface
Description: "`firecrawl_agent` with your prompt/schema → returns job ID" -- this tool pulls externally-controlled content into the agent's context window, the canonical indirect-injection vector. Even when the user supplies the URL, content at that URL can carry hostile instructions.
fix: Sandbox the fetched content: strip prompts before forwarding to the model, constrain to an allow-list of domains, and route through capframe-guard with a `domain in [...]` caveat.
OWASP LLM01NIST MEASURE-2.3ATLAS T0051
About this tool
Call is one of 4 tools exposed by firecrawl-mcp. The server scored 94/100 overall against the capframe rule engine (source: registry). Last scanned 2026-06-05.
The findings above are emitted by the public capframe.findings.v1 schema. Disagree with one? Open an issue.