deep-solve

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly documents the -t web_search flag (and RAG with --kb) for the deeptutor run command, meaning the agent can fetch and ingest public web/third‑party content that it will read and use to ground and drive its multi‑stage reasoning and actions.