qe-localization-testing
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines automated testing patterns that involve ingesting untrusted data from external web pages.
- Ingestion points: Data enters the agent context via
page.textContent()andpage.locator()in the Playwright test examples withinSKILL.md. - Boundary markers: The instructions do not implement explicit delimiters or warnings to disregard instructions that might be embedded in the test data.
- Capability inventory: The skill utilizes tools to navigate URLs (
page.goto), query databases (db.users.findOne), and coordinate multi-agent tasks via a task manager. - Sanitization: The provided snippets do not demonstrate sanitization or validation of the content retrieved from external sources before processing.
Audit Metadata