stripe
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto interact with the official Stripe API (api.stripe.com). These commands are necessary for managing customers, products, and subscriptions. It also involves writing temporary request data to/tmp/stripe_request.txtto handle form-encoded POST bodies. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests and processes data from external API responses.
- Ingestion points: API responses from
api.stripe.comas documented inSKILL.md. - Boundary markers: Absent. There are no delimiters or specific instructions for the agent to disregard potential instructions within the retrieved data.
- Capability inventory: The skill utilizes
curlfor network requests andjqfor data processing. - Sanitization: None. While
jqis used to filter fields, the content itself is not sanitized for potential injection patterns.
Audit Metadata