acp-payment-handlers
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill primarily consists of architectural documentation and instructions for building payment handlers. No malicious code or instructions to override safety guidelines were detected.- [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch technical specifications from OpenAI's developer site and documentation from GitHub. These are trusted sources for technical documentation and do not involve the execution of untrusted scripts or software.- [DATA_EXFILTRATION]: While the skill defines schemas for sensitive data such as tokenized cards and gift card PINs, it does not contain instructions for the unauthorized transmission or storage of this data. It provides an implementation guide for a legitimate commerce protocol.- [COMMAND_EXECUTION]: Although the skill specifies 'Bash' as an allowed tool, it does not provide any commands or scripts for execution. The intended use of tools is for documentation management and protocol implementation.
Audit Metadata