debugging-with-tools
Fail
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute system-level debugging and tracing commands, specifically including the use of 'sudo dtrace' in the debugger reference to acquire root privileges.
- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by ingesting untrusted content from the 'internet-researcher' agent and error messages without sanitization or boundary markers, while maintaining the capability to execute shell commands and debuggers.
Recommendations
- AI detected serious security threats
Audit Metadata