testing-skills-with-subagents
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- PROMPT_INJECTION (LOW): The document contains emphatic language and high-pressure scenarios designed to override an agent's standard reasoning process. Evidence includes directives like 'THIS IS EXTREMELY IMPORTANT' and logic stating 'If a skill existed... and you didn't use it, you failed.'
- COMMAND_EXECUTION (SAFE): The file includes standard shell commands (ls, grep) intended for local directory navigation and keyword searching within the skill library path (~/.claude/skills/).
Audit Metadata