The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes common shell commands such as npm run, npx playwright, and bash to launch the local application and execute feature-specific test suites. These actions are consistent with the skill's purpose of verifying software functionality in a development environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes project configuration from package.json and performs directory listing checks to determine which testing framework is in use. This ingestion of local data represents a surface for indirect instructions to influence agent behavior. 1. Ingestion points: Project configuration files (package.json) and directory structure analysis. 2. Boundary markers: There are no explicit markers or warnings used to isolate ingested data from the agent's instructions. 3. Capability inventory: The skill is permitted to use Bash, Write, Read, and Edit tools. 4. Sanitization: The skill does not perform validation or filtering on the content read from local files.

e2e-verify