intel-overdrive

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

• Third-party content exposure detected (high risk: 0.90). The skill requires the agent to ALWAYS call the overdrive_intel MCP tool, which "monitors 1100+ sources" and returns live public/web-sourced updates (breaking changes, feeds, action-items), meaning the agent will fetch and act on untrusted third‑party content from public sites as part of its workflow.