skill-doctor

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: Executes local bash scripts located in the plugin directory (~/.claude-octopus/plugin/scripts/) to perform environment diagnostics across 11 check categories. These scripts verify system state, hooks, and configuration.
  • [EXTERNAL_DOWNLOADS]: Recommends and facilitates the installation of standard developer tools and CLIs from well-known sources. This includes the OpenAI Codex CLI (@openai/codex via npm), the Gemini CLI from Google, and utility packages such as jq and rtk.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: Inspects local configuration files (e.g., hooks.json, state.json) and environment variables (e.g., PERPLEXITY_API_KEY) solely to verify authentication status and configuration validity. No evidence of unauthorized data transmission or exfiltration was found.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 06:35 AM