qa-playwright-ts-writer

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes test case specifications provided by other tools (e.g., qa-testcase-from-ui) which may capture untrusted web content. If these inputs contain malicious instructions, the generated test code could perform unintended actions when executed by the user.
  • Ingestion points: Inputs from qa-testcase-from-docs, qa-testcase-from-ui, and qa-manual-test-designer as described in SKILL.md.
  • Boundary markers: The skill instructions do not specify delimiters or warnings to ignore instructions embedded within the test specifications.
  • Capability inventory: The skill has the capability to write TypeScript test files to the tests/e2e directory as defined in the output_dir metadata.
  • Sanitization: No explicit sanitization or validation of the input test specifications is mentioned in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill instructions refer to the use of external packages and tools such as @playwright/mcp, @playwright/experimental-ct-react, and Context7 MCP. These are standard tools for the Playwright ecosystem and documentation fetching.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:38 PM
Security Audit — agent-trust-hub — qa-playwright-ts-writer