create-tasks
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): This skill contains no executable scripts (Python, JavaScript, Shell, etc.). It consists entirely of Markdown instructions and templates for the AI agent to follow when generating text output.
- [COMMAND_EXECUTION] (SAFE): There are no command-line executions, subprocess calls, or shell commands present in the skill.
- [DATA_EXFILTRATION] (SAFE): The skill does not perform any network requests or file system reads. While the template mentions 'path/to/file', this is a placeholder for the agent's output and does not grant the agent permission to access sensitive system files.
- [PROMPT_INJECTION] (SAFE): The instructions do not contain any patterns typical of prompt injection or bypass attempts. The 'NEVER' and 'CRITICAL' warnings within the text are internal logic constraints for the task-creation process itself.
Audit Metadata