ucp-ap2-mandates
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill is primarily educational and instructional, providing a technical overview of the AP2 protocol for autonomous agent commerce.
- [EXTERNAL_DOWNLOADS]: The instructions direct the agent to fetch documentation from ucp.dev and ap2-protocol.org, and reference a test suite in the Universal-Commerce-Protocol/conformance repository. These references are appropriate for the skill's stated purpose of implementing a specific protocol extension.
- [PROMPT_INJECTION]: The text does not contain any patterns indicative of prompt injection, such as instructions to ignore safety guidelines or override existing behavior.
- [DATA_EXFILTRATION]: No evidence was found of hardcoded credentials, sensitive file access, or unauthorized network transmissions.
Audit Metadata