adattributionkit

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

• Third-party content exposure detected (medium risk: 0.65). The runtime workflow ingests outsider-authored free text via the advertised app’s server receiving postback copies at the user-configured AttributionCopyEndpoint (HTTP POST body JSON/JWS-derived fields), which can contain attacker-controlled strings and may be forwarded into the agent/LLM context for processing.