wise-mcp

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

• Third-party content exposure detected (high risk: 0.90). The skill's required "Before you start" step explicitly instructs the agent to fetch and consume live documentation from external public URLs (https://gofastmcp.com/llms-full.txt and https://www.arcade.dev/patterns/llm.txt), meaning the agent will read untrusted third‑party web content that can directly influence its tool design and actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs fetching and using the LLM-optimized files at runtime (https://gofastmcp.com/llms-full.txt and https://www.arcade.dev/patterns/llm.txt), which would inject external, agent-directed instructions into the model's context and are described as required references for implementation.