ask-user-questions
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill uses
npx auq askto execute theauqpackage. This command downloads and executes code from the public NPM registry at runtime. - [INDIRECT_PROMPT_INJECTION]: The skill provides a mechanism for users to provide free-form text input through an 'Other' option in the TUI, which is then returned to the agent's context.
- Ingestion points: User input provided via the 'Other' text field in the interactive TUI (SKILL.md).
- Boundary markers: None identified; user responses are returned directly to the agent's conversation history.
- Capability inventory: The agent can execute shell commands via
npxand read/write based on the results of the interactive session. - Sanitization: None described; the tool passes the user's raw input back to the agent.
Audit Metadata