interactive-clarify

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and best practices for structured user interaction using the AskUserQuestion tool.
  • [SAFE]: The file contains only markdown instructions and examples, with no executable scripts or commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for ingesting user input via structured questions. 1. Ingestion points: User-selected options and text input via the AskUserQuestion tool as described in SKILL.md. 2. Boundary markers: The tool interface uses structured fields (options, headers) to separate user data. 3. Capability inventory: No file-write, network operations, or subprocess executions are defined within the skill. 4. Sanitization: Instructions do not specify input validation, relying on the underlying agent platform's safety controls.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:02 AM
Security Audit — agent-trust-hub — interactive-clarify