pm-advisor-yujun

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md:24-32 requires “俞军式研究（用 WebSearch，不编造）”，which at runtime can fetch public web pages and ingest their readable text (outsider-authored free-form content) into the agent’s LLM context, creating an indirect prompt-injection risk.