decision-prompt-builder

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are limited to providing formatting and logic guidelines for generating user interaction text. It does not include executable scripts, network requests, or system-level commands.\n- [DATA_EXPOSURE]: The skill accesses project-specific files such as planning/session_config.json and methods/Qx/qx_decisions.jsonl. These are standard application data files used to provide context for the decision prompts and do not involve sensitive system credentials or private user data.\n- [PROMPT_INJECTION]: The instructions provide a clear framework for agent behavior without any attempts to bypass safety guardrails, override system prompts, or hide malicious commands within the instructional text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 12:52 PM
Security Audit — agent-trust-hub — decision-prompt-builder