playwright-bdd
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes local project files which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: playwright.config.ts, playwright.config.js, existing .feature files, and step definition files (SKILL.md Phase 1).
- Boundary markers: No explicit markers or instructions are used to separate untrusted file content from systemic instructions.
- Capability inventory: The skill has the ability to write implementation code, modify step definitions, and execute shell commands (SKILL.md Phase 2 and 3).
- Sanitization: The skill does not perform any sanitization or validation of the ingested content.
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the project and run tests.
- Evidence: npx bddgen && npx playwright test (SKILL.md Phase 3).
- Evidence: npx bddgen export (SKILL.md Scenario Writing Rules).
Audit Metadata