agency-zhihu-strategist

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow (e.g., “Topic Research”, “Question Source Identification”, “Competitive Analysis”) implies fetching/analyzing existing Zhihu/public expert answers and trending questions, which are outsider-authored free text that would be ingested into the agent’s LLM context for synthesis.