connect-ai-stripe

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing data from external sources.
  • Ingestion points: The agent reads data from Stripe tables including Customers, Invoices, Products, and ThinEvents (SKILL.md, references/stripe.md, references/stripev2.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the retrieved Stripe data.
  • Capability inventory: The agent is granted capabilities to perform state-changing operations via stored procedures, such as CancelSubscription, CapturePaymentIntent, and VoidInvoice (references/stripe.md).
  • Sanitization: There are no instructions for sanitizing or validating the content of the retrieved records before the agent processes or acts upon them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 04:50 PM
Security Audit — agent-trust-hub — connect-ai-stripe