ucp-payment-handlers
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were identified within the skill instructions or metadata.
- [EXTERNAL_DOWNLOADS]: The skill references and fetches documentation from official developer platforms including Google Pay (developers.google.com), Shop Pay (shopify.dev), and the UCP project repository (ucp.dev). These references are used for legitimate architectural guidance.
- [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it fetches external data and has write capabilities, though the risk is mitigated by the use of trusted sources.
- Ingestion points: External documentation fetched via
WebFetchfrom Google and Shopify. - Boundary markers: None explicitly defined for the fetched content.
- Capability inventory: Permissions include
Bash,Write, andEdittools. - Sanitization: No specific sanitization mentioned for the fetched content.
Audit Metadata