The Agent Skills Directory

Command Execution: The skill performs shell-based operations, including running build and test scripts (npm run build, npm run test:sites) and executing a preflight script from the user context. These actions are standard for deployment workflows but involve executing code within the local environment.
Indirect Prompt Injection Surface: The skill ingests data from external sources such as codebase paths, design systems, and Figma files. If these sources contain malicious instructions, they could potentially influence the agent's operations during the deployment workflow.
Prompt Injection Patterns: The inclusion of a 'Critical Overrides' section uses language typically associated with instruction bypass to link to essential operational guidelines.

share