telegram
Warn
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (
touch,rm, andtest) to manage a state file located at/tmp/claude_telegram_active. - [COMMAND_EXECUTION]: The instructions explicitly direct the agent to set
dangerouslyDisableSandbox: truewhen running these commands. This configuration intentionally circumvents the security boundaries intended to isolate the agent's execution environment, which is an unsafe practice for simple file operations in temporary directories.
Audit Metadata