adcp-brand

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

• Third-party content exposure detected (low risk: 0.10). The agent searches and retrieves external licensable rights descriptions via get_rights, which involves active search/fetching of third-party content rather than automated monitoring of an inbox or feed.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (medium risk: 0.30). The skill executes AdCP Brand Protocol operations, including acquire_rights which acquires brand/talent licensing rights based on pricing options for campaigns. This constitutes a direct purchase/licensing transaction operation. However, the skill documentation specifies that real agents use OAuth for authorization (e.g., SKILL.md:57, 172), establishing independent service-level authentication and access control.