stripe-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (Stripe) and has the capability to perform sensitive actions like creating charges and refunds, creating a potential attack surface if data in the Stripe account is malicious.
- Ingestion points: Tools like
STRIPE_SEARCH_CUSTOMERS,STRIPE_LIST_INVOICES, andSTRIPE_LIST_PRODUCTSingest potentially untrusted data from the Stripe account into the agent's context (SKILL.md). - Boundary markers: No specific boundary markers or instructions to ignore embedded content in Stripe data are provided to the agent.
- Capability inventory: The skill possesses significant capabilities to modify the environment, including tools such as
STRIPE_CREATE_PAYMENT_INTENT,STRIPE_POST_CHARGES_CHARGE_REFUNDS, andSTRIPE_CREATE_CUSTOMER(SKILL.md). - Sanitization: No sanitization, validation, or filtering of the external content retrieved from Stripe is described.
Audit Metadata