stripe-implementation-planner

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • External Package Installation: The skill instructs the agent to install the @stripe/cli package from the NPM registry if it is not already available. This is a standard procedure to provide the necessary planning tools, utilizing the official vendor-supported package.
  • Command Execution: The skill relies on official Stripe CLI commands such as stripe tools plan and stripe sandbox create to generate integration architecture recommendations. These commands are scoped to the development environment and are part of the vendor's toolset.
  • Indirect Prompt Injection Surface: The skill processes user-provided business and implementation context which is then passed to external tools. This represents a potential surface for indirect prompt injection, as instructions embedded within the user's business description could theoretically influence the agent's summary or the tool's behavior.
  • Ingestion points: User-provided business model, payment models, and sales channel details interpolated into the stripe tools plan --message command.
  • Boundary markers: The skill relies on the agent to gather and describe needs accurately but does not specify explicit delimiters for the message payload.
  • Capability inventory: The skill possesses the capability to execute shell commands and create test sandboxes.
  • Sanitization: The instructions focus on content accuracy and requirement preservation rather than explicit string sanitization for the command-line payload.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 04:09 AM