agent-stripe
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFE
Full Analysis
- [CREDENTIALS_SAFE]: The skill implements strong credential security practices. It explicitly forbids the agent from requesting API keys in chat and instructs the use of secure local OS dialogs for authentication. Keys are stored in the system Keychain rather than insecure configuration files.
- [DATA_EXPOSURE]: A robust redaction policy is built into the tool's output. Sensitive fields such as customer PII, secrets, and private URLs are masked by default. The skill requires explicit user intent via the
--exposeflag to reveal specific redacted fields, and it never exposes stored API keys. - [COMMAND_EXECUTION]: The skill uses a dedicated
agent-stripeCLI for investigations. The provided instructions are centered on read-only actions and 'investigate' commands that aggregate data safely, with warnings about the high stakes of live-mode actions.
Audit Metadata