adattributionkit

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

• Third-party content exposure detected (high risk: 0.80). The skill's required server workflow (SKILL.md "Opt in to receive winning postback copies" and references/adattributionkit-patterns.md "Server-Side Postback Handling") instructs operators to accept and parse HTTPS POST postbacks from external devices/servers (untrusted third-party inputs) and to act on the JSON/JWS payloads for attribution decisions, so third-party content is ingested and can materially influence actions.