playwright-test-data-isolation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements patterns that ingest data from external application APIs into the test execution context, creating a potential surface for indirect prompt injection if the target application's API returns untrusted or malicious content.
- Ingestion points: Data is ingested through API responses in
SKILL.md(e.g., thegetProjectIdByNamefunction parsing JSON from/api/internal/workspaces/...). - Boundary markers: The skill does not provide specific delimiters or instructions to the agent to treat data from the target application as untrusted.
- Capability inventory: The skill guides the creation of scripts with browser automation (Playwright), network request (
APIRequestContext), and local filesystem access (for storingstorageState). - Sanitization: The code includes
encodeURIComponentfor outgoing request parameters, but lacks validation or sanitization for the data received in API response bodies.
Audit Metadata