soia-cwork-processon-diagrams

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md’s required workflow uses the ProcessOn browser runner to visit customer-specified ProcessOn pages/URLs and ingest their readable DOM text/snapshots (bounded_snapshot visible_text) into JSON returned to the agent, which is then available for the LLM; this is an indirect prompt-injection exposure via arbitrary web content.