design-command-line-interfaces
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The bundled script
scripts/check_cli.pyutilizessubprocess.runandsubprocess.Popento execute command-line programs provided as arguments. This is the core functionality intended to probe a CLI's behavior for compliance with design guidelines. The skill's documentation explicitly cautions that it executes the command and should only be used on trusted code. - [INDIRECT_PROMPT_INJECTION]: The skill's verification process in
scripts/check_cli.pyingests data from standard output and error streams of external CLI tools. While this represents a potential surface for processing untrusted data, the analysis is restricted to identifying specific patterns. - Ingestion point:
scripts/check_cli.pycaptures and analyzes the terminal output of target CLI programs during its verification runs. - Boundary markers: None present for the ingested command output.
- Capability inventory: The skill possesses command execution capabilities through
subprocess.runandsubprocess.Popeninscripts/check_cli.pyand evaluation scripts. - Sanitization: Output analysis is limited to regex matching (detecting language-specific stack traces and ANSI escape sequences) and keyword verification (searching for 'usage' in help text) to report design violations.
Audit Metadata