higgsfield-creative
Warn
Audited by Snyk on May 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill performs runtime tool discovery and calls via the Higgsfield MCP endpoint (https://mcp.higgsfield.ai/mcp), whose returned tool schemas directly determine accepted inputs and prompt structure and are required for generation, so external content can control prompts.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata