local-llm-setup

Warn

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Python scripts and system commands to manage background services. It specifically uses launchd, systemd, and NSSM to install a routing proxy as a persistent daemon on the host operating system.
  • [EXTERNAL_DOWNLOADS]: The documentation indicates that the skill performs automated downloads of llama-server binaries and model files from external sources. While specific URLs are not explicitly listed in the SKILL.md file, the intended functionality involves fetching and potentially executing third-party binary content.
  • [PROMPT_INJECTION]: The run_agent.py script ingests external data, which creates a vulnerability to indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context via external code files (e.g., target.py) and persona definitions (e.g., agents/refactor-expert.md).
  • Boundary markers: No delimiters or safety instructions are specified to prevent the agent from following commands embedded within the processed files.
  • Capability inventory: The skill has the ability to write to the file system (e.g., output.md) and execute Python-based agent logic.
  • Sanitization: There is no mention of sanitization, validation, or filtering of the content ingested from external files before it is processed by the LLM.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 12, 2026, 08:07 PM
Security Audit — agent-trust-hub — local-llm-setup