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
cofoundertool. - 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