parallel-deep-research

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run "parallel-cli research run" and "parallel-cli research poll" (Step 1 and Step 2), which fetches open-web research and produces an executive summary plus $FILENAME.md and $FILENAME.json derived from third‑party sources that the agent is expected to read/share, exposing it to untrusted external content.