tui-front-ui

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a domain-specific language for design operations and explicitly instructs the agent to execute these operations through the batch_design tool. This involves generating and running automated design scripts.- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8) by interpolating user-provided design requirements into executable tool commands without sanitization.
  • Ingestion points: User requests defining UI elements, text values, and layout parameters enter the agent's context through the skill's primary interface.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat user input as data and prevent it from affecting the structure of the generated DSL calls.
  • Capability inventory: The skill employs several potentially powerful tools within the design environment, including batch_design, open_document, snapshot_layout, and get_screenshot.
  • Sanitization: There is no mention of sanitizing, escaping, or validating user-supplied text before it is inserted into the PENCIL_BATCH_DESIGN or JSON specification blocks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:15 AM
Security Audit — agent-trust-hub — tui-front-ui