testing-uis
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with and analyze external, potentially untrusted web pages and UIs, which serves as an ingestion point for external data.
- Ingestion points: The agent renders and interacts with external web applications via the browser or Playwright (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore instructions embedded within the target UI are provided in the skill instructions.
- Capability inventory: The agent performs browser interactions, captures snapshots, reads console logs, and uses Playwright for automation (SKILL.md).
- Sanitization: The skill does not specify sanitization or filtering protocols for the content of the UI being tested.
- [COMMAND_EXECUTION]: The skill instructs the agent to use Playwright for browser automation. It includes a safety-conscious instruction to walk the user through setup rather than assuming it is configured or performing silent execution (SKILL.md).
Audit Metadata