adcp-media-buy
Pass
Audited by Gen Agent Trust Hub on May 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes an ingestion point for untrusted data via the natural language
briefparameter in theget_productstask. - Ingestion point: The
brieffield in theget_productsrequest (defined inSKILL.md) accepts natural language campaign requirements. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the
briefcontent. - Capability inventory: The skill uses MCP tools (
get_products,create_media_buy,sync_creatives,get_media_buy_delivery) to interact with advertising agents and manage monetary budgets. - Sanitization: No sanitization or validation logic is specified for the user-provided brief before it is processed by the agent.
Audit Metadata