tapcart-blocks
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
tapcartCLI tool to perform project management tasks, including file creation, synchronization, and local server management. These commands are restricted to the functionality of the vendor-provided tool. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes data pulled from an external source.
- Ingestion points: Content is fetched from the Tapcart dashboard into the local environment via the
tapcart block pullandtapcart component pullcommands specified inSKILL.md. - Boundary markers: The instructions do not define boundary markers or explicit safety warnings to help the agent distinguish between its system instructions and the content pulled from the dashboard.
- Capability inventory: The agent possesses the capability to execute shell commands (via the
tapcartCLI), write to the local file system, and manage network processes (dev server). - Sanitization: The skill lacks documentation for sanitizing, validating, or escaping the external JSX and JSON data retrieved during the synchronization process.
Audit Metadata