write-a-plan

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

• Third-party content exposure detected (high risk: 0.80). The skill's Step 4 "Gather external context" explicitly instructs the agent to use MCP tools to pull in content from external tools (e.g., Linear issues, Figma designs, Notion docs), meaning it will fetch and interpret user-generated third-party content that can materially influence planning decisions.