caam

Fail

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPERSISTENCECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The installation instructions in SKILL.md use a curl | bash pattern to execute a script directly from a remote GitHub repository. This gives the external script full execution privileges on the user's system.
  • [EXTERNAL_DOWNLOADS]: The setup process downloads an installation script from raw.githubusercontent.com/Dicklesworthstone/coding_agent_account_manager/main/install.sh.
  • [DATA_EXFILTRATION]: The skill is designed to read, store, and restore high-value authentication files including ~/.claude.json, ~/.config/claude-code/auth.json, ~/.codex/auth.json, and ~/.gemini/oauth_credentials.json, which contain session tokens for paid AI services. Additionally, the 'Isolated Profiles' feature symlinks the user's ~/.ssh and ~/.gitconfig directories into its own vault, exposing private keys and configuration.
  • [PERSISTENCE]: The documentation instructs the agent or user to modify shell profile files (~/.bashrc or ~/.zshrc) to create aliases for standard CLI tools. This ensures the skill's wrapper logic intercepts and manages sessions across all terminal sessions.
  • [COMMAND_EXECUTION]: The caam run and caam exec commands facilitate tool management by launching subprocesses with manipulated environment variables such as $HOME and $CODEX_HOME.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/Dicklesworthstone/coding_agent_account_manager/main/install.sh?$(date - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Nov 4, 2026, 09:51 AM