plannotator

Fail

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The installation process described in scripts/install.sh and SKILL.md uses the curl -fsSL https://plannotator.ai/install.sh | bash pattern, which executes unverified remote code with the current user's privileges.
  • [COMMAND_EXECUTION]: Setup scripts including setup-hook.sh, setup-gemini-hook.sh, and setup-codex-hook.sh modify configuration files such as ~/.claude/settings.json, ~/.gemini/settings.json, and ~/.codex/config.toml to add execution hooks. These hooks are designed to trigger the plannotator command automatically whenever specific agent modes are exited, providing the skill with persistent execution capabilities.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes scripts from https://plannotator.ai. This domain is not identified as a trusted vendor or well-known technology service.
  • [DATA_EXFILTRATION]: The skill provides a feature to share plan reviews via share.plannotator.ai. This involves uploading local git diffs and implementation plans, which may contain sensitive source code or internal project details, to an external server.
  • [COMMAND_EXECUTION]: The scripts/configure-remote.sh script modifies shell profile files such as .zshrc and .bashrc to inject environment variables, which is a technique used to persistently alter the user's shell environment.
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
Risk Level
CRITICAL
Analyzed
Mar 9, 2026, 11:58 AM