qe-compatibility-testing

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to automate interactions with external websites using Playwright and cloud testing platforms. This functionality inherently processes untrusted data from the web, which could contain instructions intended to manipulate the agent's behavior.
  • Ingestion points: The skill utilizes the url parameter within the Task definition and page.goto() calls in the provided Playwright snippets (SKILL.md) to load external content.
  • Boundary markers: There are no explicit instructions or delimiters defined to isolate the content of the target URL or to warn the agent about potential instructions embedded within the processed pages.
  • Capability inventory: The skill leverages Playwright for web automation and interacts with the BrowserStack API for cross-device coverage, providing the agent with significant interaction capabilities over the retrieved content.
  • Sanitization: The skill does not include mechanisms for filtering or sanitizing the content retrieved from external URLs before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:15 PM
Security Audit — agent-trust-hub — qe-compatibility-testing