playwright-e2e-builder
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill instructs the agent to 'Check .env files for test-specific environment variables' during its exploration phase. Files named .env are a standard location for sensitive information such as API keys, database credentials, and production secrets, making this a high-risk operation.
- [INDIRECT_PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it ingests data from potentially untrusted local files and user input to generate Playwright test scripts and GitHub Action workflows.
- Ingestion points: The agent reads project configuration files, router configs, and .env files in Phase 1, and collects user data in Phase 2.
- Boundary markers: No delimiters or specific instructions to ignore embedded malicious content are provided for the file scanning process.
- Capability inventory: The skill leads to the creation of TypeScript files and CI YAML files, and it generates an ApiClient fixture that uses the fetch API for network requests.
- Sanitization: The skill does not provide methods for validating or sanitizing the content retrieved from the file system before using it in code generation.
Audit Metadata