playwright-e2e-tester
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to generate test code based on user stories and acceptance criteria. This represents an indirect prompt injection surface if the provided stories contain malicious instructions designed to alter the agent's behavior.
- Ingestion points: User-provided acceptance criteria and stories mentioned in the 'Capabilities' section (SKILL.md).
- Boundary markers: None present in the skill instructions.
- Capability inventory: Generation of test scripts that perform file system operations and network requests via the Playwright framework.
- Sanitization: Not explicitly specified; the skill relies on the model's inherent safety guardrails.
- [EXTERNAL_DOWNLOADS]: The provided CI/CD examples include steps to download browser binaries and system dependencies required for Playwright to function.
- Evidence: The GitHub Actions example in SKILL.md includes the command
npx playwright install --with-depsto fetch necessary browser engines.
Audit Metadata