playwright-qa
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could theoretically contain malicious instructions to influence the agent.\n
- Ingestion points: Workflow descriptions in
SKILL.mdandmanual-to-automated.mdspecify processing external tickets, PRDs, and CSV/spreadsheet exports from test management tools like TestRail or Xray.\n - Boundary markers: The instructions do not provide explicit guidance for the agent to use delimiters (e.g., XML tags or triple backticks) or "ignore embedded instructions" warnings when handling these external files.\n
- Capability inventory: The skill assists in generating, converting, and reviewing Playwright test code. If the input data is malicious, it could attempt to manipulate the generated code to include unauthorized network requests or file system operations.\n
- Sanitization: The skill lacks instructions for the agent to validate or sanitize the content of requirements or manual test cases before they are transformed into automated specs.
Audit Metadata