skills/kursku/skills/local-llm-expert/Gen Agent Trust Hub

local-llm-expert

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional, focusing on technical advice for local AI deployment and hardware optimization. It does not contain executable scripts or hidden logic.
  • [PROMPT_INJECTION]: No instructional overrides, jailbreak patterns, or attempts to bypass safety filters were found.
  • [DATA_EXFILTRATION]: No access to sensitive local files (e.g., credentials, SSH keys) or network exfiltration patterns were identified.
  • [REMOTE_CODE_EXECUTION]: While the skill suggests command-line tools for local model inference, it does not include instructions for downloading or executing unverified remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 05:49 PM
Security Audit — agent-trust-hub — local-llm-expert