disting-nt-lua-scripter

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of Lua code based on user-provided descriptions, which presents a surface for indirect prompt injection. Malicious instructions could potentially be embedded in user prompts or in external data streams (like MIDI or I2C) processed by the generated scripts.
  • Ingestion points: User-provided specifications for Lua scripts in SKILL.md and templates/template.lua.
  • Boundary markers: Absent; there are no explicit instructions to the agent to delimit or sanitize user-provided logic from the script structure.
  • Capability inventory: The target hardware environment supports script execution, library loading (require), MIDI and I2C communication, and persistent state management (serialise). All scripts share a single global Lua environment, which is a platform-specific design choice that could allow cross-script interference if not managed carefully.
  • Sanitization: Absent; the skill provides templates and examples but does not include patterns for validating or escaping inputs from external hardware sources.
  • [DYNAMIC_EXECUTION]: The skill generates Lua source code that is intended for execution on a hardware module. The environment supports dynamic library loading via the require function, and all scripts share a single global state, which increases the impact of potential script-based exploits.
  • Execution method: The generated Lua scripts are loaded and executed by the Disting NT firmware at a 1000Hz control rate.
  • Dynamic patterns: Usage of require to load external libraries from the module's filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 02:15 AM
Security Audit — agent-trust-hub — disting-nt-lua-scripter