tui-line-progress
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines static formatting and rendering rules for UI components. No signs of command execution, data exfiltration, or obfuscation were found.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data through a JSON input model.\n
- Ingestion points: SKILL.md defines fields like
modelValueandstate.errorin the Input Model section that process data at runtime.\n - Boundary markers: Instructions require the agent to use specific markdown code blocks and headers (e.g.,
OUTPUT: TUI_RENDER) to separate its analysis from output.\n - Capability inventory: The skill is restricted to text generation and lacks capabilities for file writing, network communication, or system command execution.\n
- Sanitization: Rendering rules specify that error messages must be truncated, reducing the risk of content-based layout exploitation.
Audit Metadata