wjx-mcp-use

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

• Third-party content exposure detected (high risk: 0.90). The skill's core workflow and toolset (e.g., query_responses and decode_responses in SKILL.md and references/tools-response.md) explicitly fetch and ingest user-generated survey responses from the Wenjuanxing platform, which the agent is expected to read/analyze (get_report, detect_anomalies) and thus could allow untrusted third-party content to influence subsequent actions.