notion-spec-to-implementation

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

• Third-party content exposure detected (high risk: 0.70). The skill fetches and parses the Notion spec page content at runtime via Notion:notion-fetch (Step 1.3/1.2), and that spec text is outsider-authored unless the operating user authored it, creating indirect prompt-injection risk through LLM context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill declares and uses the external Notion MCP endpoint (https://mcp.notion.com/mcp) at runtime to fetch Notion spec pages which are injected into the agent's context and thus can directly control prompts/output, and access to that endpoint is a required runtime dependency.