mcp-creator

Warn

Audited by Snyk on Mar 8, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to "Consult Live Documentation" by fetching external web docs (e.g., https://gofastmcp.com/llms-full.txt, site:web searches) and to load user-supplied OpenAPI/FastAPI specs, so the agent will read and act on arbitrary third‑party web content that can change implementation decisions ("live docs win").

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill explicitly directs runtime fetching of live LLM-optimized documentation from https://gofastmcp.com/llms-full.txt and states "live docs win," meaning the fetched content is a required runtime dependency that will directly influence prompts/instructions, so this URL can control agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 04:45 PM