ai-ethics-auditor

对AI系统进行偏见、公平性与隐私方面的审计。分析提示词与数据集，确保AI的实施既合乎伦理又安全可靠。

SKILL.md

--- frontmatter

name: ai-ethics-auditor
description: Audits AI systems for bias, fairness, and privacy. Analyzes prompts and datasets to ensure ethical and safe AI implementation.
status: implemented

AI Ethics Auditor

This skill protects your organization by ensuring AI implementations are fair, unbiased, and respect user privacy.

Capabilities

1. Bias & Fairness Audit

•Analyzes prompts for stereotypical or discriminatory language.
•Checks if datasets contain historical biases that could lead to unfair AI decisions.

2. AI Safety Verification

•Verifies that PII (Personally Identifiable Information) is not leaked through AI responses.
•Audits for "dark patterns" in AI-driven user interactions.

Usage

•"Audit our RAG prompt for potential gender or racial bias."
•"Perform an ethics check on this customer support chatbot dataset."

Knowledge Protocol

•This skill adheres to the knowledge/orchestration/knowledge-protocol.md. It automatically integrates Public, Confidential (Company/Client), and Personal knowledge tiers, prioritizing the most specific secrets while ensuring no leaks to public outputs.