bot-process-control
Warn
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to manage system processes and persistence via
launchctl,pkill, andpgrep, including the management oflaunchdplist files in~/Library/LaunchAgents/. - [CREDENTIALS_UNSAFE]: The skill provides instructions for interacting with sensitive OAuth token files in
~/.claude/tools/gmail-tokens/and references secret storage within a 1Password vault. - [PROMPT_INJECTION]: The skill includes 'Self-Evolving' instructions that command the agent to modify the skill's own source code (
SKILL.md) based on runtime performance, which can lead to unintended logic changes or behavioral drift.
Audit Metadata