workflow-housekeep
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). This workflow includes runtime web research via
CallMcpTool(... server: "user-firecrawl", toolName: "firecrawl_search", arguments: { "sources": [{ "type": "web" }] }), which can ingest arbitrary outsider-authored free text from fetched public web pages into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata