stripe
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for building endpoints that process external data from Stripe (webhooks) and client-side requests, creating a potential attack surface where malicious data could attempt to influence the agent's behavior. The skill mitigates this by teaching proper verification techniques.
- Ingestion points: External data enters the system through API routes using 'request.json()' and webhook handlers using 'request.text()' in SKILL.md.
- Boundary markers: The skill implements Stripe signature verification in the webhook handler, which serves as a security boundary to ensure data originates from a trusted source.
- Capability inventory: The provided code snippets include capabilities to create payment intents, manage customer records, and modify subscription states via the Stripe SDK.
- Sanitization: The skill explicitly demonstrates sanitizing incoming webhook data by using 'stripe.webhooks.constructEvent' to verify signatures before any processing occurs.
Audit Metadata