story-deslop

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly describes workflows where users "贴一段文字" and the Phase 1/Phase 4 detection and rewriting steps ingest and act on user-submitted text (user-provided/untrusted content) as part of its runtime, so arbitrary third-party/user content can influence the agent's processing and actions.