ask-questions-if-underspecified
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions are focused on requirement clarification and follow safe interaction patterns. It limits the number of questions to avoid user fatigue and provides defaults to streamline the process.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to interact with local files in the .claude/context/memory/ directory for session persistence. These commands are restricted to the skill's own memory management and do not access sensitive user data or system files.
- [PROMPT_INJECTION]: While the skill processes user-supplied requirements, it instructs the agent to respond with a specific, limited format (clarifying questions with defaults), which mitigates the potential for the agent to be diverted into unauthorized behaviors via indirect prompt injection.
Audit Metadata