generate
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
npx playwright testto verify generated code, which runs shell commands in the local environment. - [DYNAMIC_EXECUTION]: The skill dynamically creates JavaScript or TypeScript test files by interpolating user-provided behavior and project source code into templates, then executes these generated files.
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted input from user arguments and the local codebase to generate executable test scripts without explicit sanitization or boundary markers.
- Ingestion points: User-provided behavior descriptions ($ARGUMENTS) and local project files (e.g., components,
playwright.config.ts,auth.setup.ts). - Boundary markers: The instructions do not define delimiters to separate untrusted data from the prompt logic.
- Capability inventory: The skill can perform file system writes and execute shell commands (
npx). - Sanitization: There is no requirement or evidence of sanitization for the input data before it is included in generated code.
Audit Metadata