run-testing-session
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes Playwright commands (e.g.,
npx playwright test) to run generated tests. This is the primary function of the orchestrator and is performed within the local environment. - [DATA_EXFILTRATION]: The skill processes user-provided test specifications and base URLs. Analysis of the orchestrator logic confirms that data is handled locally within the
docs/playwright-spec-testing/directory, with no unauthorized external transmission detected. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) as it ingests untrusted data from user-provided 'Spec input' and output files generated by subagents.
- Ingestion points: User-provided test specifications, base URLs, and output files from subagents (e.g.,
test-plan.md). - Boundary markers: None. The skill does not implement specific delimiters or 'ignore' instructions for the ingested content.
- Capability inventory: The orchestrator has the capability to execute shell commands (
npx playwright) and manage file system operations within the project scope. - Sanitization: None. The content of the spec input and subagent responses is used directly to drive the pipeline stages.
Audit Metadata