playground
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute the
open <filename>.htmlcommand. This is used to launch the generated interactive tool in the user's default web browser. This is standard behavior for local development tools. - [PROMPT_INJECTION]: The skill defines a pattern for 'Indirect Prompt Injection' where the generated HTML playground creates a natural language prompt based on user interaction. This prompt is designed to be copied and pasted back into the agent to guide subsequent actions. While this is an attack surface, it is the primary intended functionality of the skill and involves a 'user-in-the-loop' step.
Audit Metadata