outlit

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

• Third-party content exposure detected (high risk: 0.90). Yes — SKILL.md explicitly instructs the agent to run searches and fetch source artifacts (e.g., "outlit search", "outlit sources get", "sources list") which return untrusted user-generated content such as EMAILs, SUPPORT_TICKETs, CALLs and other third‑party artifacts that the agent is expected to read and use as evidence to drive decisions.