Skills
skills/aaaaqwq/claude-code-skills/agent-model-switcher/Gen Agent Trust Hub

agent-model-switcher

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The Python script switch_model.py performs local file system operations, including reading, writing, and copying JSON configuration files (agent.json and models.json) located in the ~/.openclaw/agents directory.
  • [CREDENTIALS_UNSAFE]: The skill reads sensitive configuration files to extract LLM provider API keys. The list command displays the first 20 characters of detected zai provider keys in the terminal output. While the output is partially masked, this represents a practice of exposing credential data in command-line interfaces.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 10:32 PM
Security Audit — agent-trust-hub — agent-model-switcher