cursor-rescue

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell scripts (e.g., resolve-impl-backend.sh, set-impl-backend.sh, model-routing.sh, and setup-cursor.sh) located in a directory derived at runtime from environment variables such as HARNESS_PLUGIN_ROOT, CLAUDE_PLUGIN_ROOT, or CLAUDE_SKILL_DIR.
  • [COMMAND_EXECUTION]: The skill attempts to locate and execute the cursor-agent binary by searching the system PATH and the $HOME/.local/bin directory to verify its version and status.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 08:22 AM
Security Audit — agent-trust-hub — cursor-rescue