dpa-review

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly ingests user-supplied DPA PDFs and directs the agent to "检索当前有效的出境机制/检索每个适用制度的现行有效规则" (including an explicit "[联网检索 — 需复核]" branch), which means it reads and acts on external/untrusted user- or web-sourced legal/regulatory content as part of its decision-making.