# LLM Prompt Risk Auditor

> Inspect database operation requests for ambiguity and unsafe intent using deterministic rules.

- Skill: `rweisssieker-xp/llm-prompt-risk-auditor` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rweisssieker-xp/llm-prompt-risk-auditor`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rweisssieker-xp/llm-prompt-risk-auditor/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: rweisssieker-xp (https://skillmd.com/u/rweisssieker-xp)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rweisssieker-xp/llm-prompt-risk-auditor

---


# llm_prompt_risk_auditor

Use this skill to audit natural-language AI prompts or generated SQL instructions for dangerous ambiguity and unsafe production intent.

Governance:
- Never execute the prompt.
- Block or escalate destructive, broad, or production-scoped instructions.
- Rewrite unsafe requests as scoped dry-run diagnostics.

Output contract:
- `usp: "llm_prompt_risk_auditor"`
- `decision`, `risks`, `safeRewrite`
- `evidence`, `confidence`, `source: "analysis"`