stripe-app-builder

Pass

Audited by Gen Agent Trust Hub on Jun 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to interact with Stripe through a CLI tool named cofounder (e.g., cofounder run get_stripe_connection_status, cofounder run sync_stripe_env). This allows the agent to perform administrative actions such as resource creation and environment synchronization.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes and acts upon untrusted user input regarding business logic and subscription models.
  • Ingestion points: User-provided descriptions of products, plans, and pricing models serve as the primary input for determining which Stripe actions to perform.
  • Boundary markers: The skill instructions do not specify the use of delimiters (e.g., XML tags or triple backticks) to isolate user data from the agent's instructions.
  • Capability inventory: The agent possesses significant capabilities, including the ability to execute CLI commands and modify application environment variables via the cofounder tool.
  • Sanitization: There is no explicit requirement for the agent to sanitize or validate user-provided strings before they are used in generated code or passed to tool arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 9, 2026, 09:34 PM
Security Audit — agent-trust-hub — stripe-app-builder