parallel-deep-research

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md instructs running "parallel-cli research run" and polling results which use cached and live web data and write an executive summary/$FILENAME.md from open public sources, so the skill clearly fetches and ingests untrusted third‑party web content that the agent is expected to read/interpret as part of its workflow.