ap2-merchant-agent
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches protocol specifications and technical documentation from
ap2-protocol.organd reference implementations from GitHub repositories.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external Intent Mandates from third-party Shopping Agents, which represents an untrusted data ingestion surface. - Ingestion points: Incoming Intent Mandates are parsed from external agents as described in SKILL.md.
- Boundary markers: No specific delimiters are defined in the implementation guide for separating external instructions from agent prompts.
- Capability inventory: The skill utilizes tools including Bash, Write, WebFetch, and Edit, which provide significant control over the environment.
- Sanitization: The skill explicitly recommends implementing validation for incoming mandates to ensure authenticity and integrity.
Audit Metadata