omu
Fail
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The
scripts/install.shscript fetches and executes a shell script directly fromhttps://plannotator.ai/install.shusingcurl -fsSL ... | bash. This allows arbitrary code execution from a third-party source not included in the trusted vendor list.\n- [EXTERNAL_DOWNLOADS]: The skill downloads and installs various components and tools from unverified third-party sources, including domains such asplannotator.aiand GitHub repositories not listed as trusted.\n- [COMMAND_EXECUTION]: Multiple scripts, includingsetup-claude.sh,setup-codex.sh,setup-gemini.sh, andsetup-opencode.sh, programmatically modify the AI agent's global configuration files located in the user's home directory (e.g.,~/.claude/settings.json,~/.codex/config.toml,~/.gemini/settings.json).\n- [REMOTE_CODE_EXECUTION]: The setup process injects automated execution hooks into the AI agent's environment, such asExitPlanModefor Claude Code andnotifyfor Codex. These hooks are configured to automatically trigger the execution of local scripts or external binaries likeplannotatorin response to agent lifecycle events.\n- [COMMAND_EXECUTION]: The cleanup scriptscripts/worktree-cleanup.shexecutes git commands to prune worktrees and includes functionality to force-remove directories, which can lead to the deletion of uncommitted changes.
Recommendations
- HIGH: Downloads and executes remote code from: https://plannotator.ai/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata