ai-agent-discovery-and-qualification

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 instructs using the “buyer’s brief” and related “buyer evidence” as domain inputs; since those are outsider-authored by the buyer (not the operating user), free-form buyer text is fed into the agent’s LLM context during the discovery workflow.