tui-line

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a template-driven documentation file. It does not include any executable scripts, shell commands, or network operations. All instructions are focused on text and JSON generation for design workflows.
  • [PROMPT_INJECTION]: Indirect prompt injection surface analysis:
  • Ingestion points: Untrusted data enters the agent context through the JSON 'Input Model' defined in the instructions.
  • Boundary markers: The skill lacks instructions for using delimiters or safety markers to isolate user-provided data from agent instructions.
  • Capability inventory: The skill has no access to exploitable capabilities such as file system writes, network requests, or shell execution.
  • Sanitization: No input validation or escaping mechanisms are described for the processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:07 PM
Security Audit — agent-trust-hub — tui-line