createcli
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEPRIVILEGE_ESCALATIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill incorporates security best practices by requiring a 'dry-run' mode for destructive operations and forbidding the hardcoding of credentials.
- [PRIVILEGE_ESCALATION]: The skill uses
chmod +xto modify permissions on dynamically created script files, which is necessary for their execution. - [DYNAMIC_EXECUTION]: The tool generates executable code in Bash, TypeScript, and Python based on user input, which is the primary intended behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user descriptions as part of its code generation workflow. It lacks explicit boundary markers or input sanitization, while possessing the 'Write' and 'Bash' capabilities needed to create and run the resulting scripts.
- [COMMAND_EXECUTION]: The workflow includes running the generated scripts to test functionality and verify help text.
Audit Metadata