ap2-cart-mandate
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill's primary function is to guide an agent through the implementation of a commerce protocol by fetching public documentation and referencing standard JSON schemas.
- [PROMPT_INJECTION]: The skill instructs the agent to fetch documentation from
ap2-protocol.organd search GitHub for official Google repositories. While this introduces an indirect prompt injection surface by ingesting external content, it is categorized as safe because it targets legitimate technical documentation and trusted vendor repositories necessary for the skill's primary purpose. - Ingestion points:
SKILL.md(viaWebFetchandWebSearchinstructions). - Boundary markers: Absent.
- Capability inventory:
Read,Write,Edit,Bash,Grep,Glob,WebSearch,WebFetchtools are enabled to allow for code implementation and testing. - Sanitization: Absent, though the source targets are restricted to the protocol specification and official vendor repositories.
Audit Metadata