adcp-media-buy
Warn
Audited by Snyk on Oct 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill executes the AdCP Media Buy Protocol by interacting with advertising sales agents, where product discovery via natural language briefs and catalog synchronization ingest ad products and listings from external publisher agents.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 0.70). The skill operates the AdCP Media Buy Protocol, which includes purchasing advertising campaigns and committing funds via
create_media_buy(SKILL.md:117-155). This constitutes a direct financial operation (purchases/charges). Although authentication errors are mentioned (SKILL.md:407), the skill specification itself does not document an independent, service-enforced access control or authorization mechanism gating the direct financial routes (beyond application-level protocol parameters). Therefore, it falls under direct operations without established qualifying independent control.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata