dcl-policy-enforcerInstruction-only compliance checker for AI outputs. Detects jailbreaks, prompt injection, EU AI Act violations, GDPR breaches, unsafe financial and medical a...
Install via ClawdBot CLI:
clawdbot install daririnch/dcl-policy-enforcerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"ignore previous instructions"Sends data to undocumented external endpoint (potential exfiltration)
POST → https://webhook.fronesislabs.com/evaluateCalls external URL not in known-safe list
https://webhook.fronesislabs.com/evaluateAI Analysis
The skill sends all evaluated AI outputs to an external, undocumented endpoint (https://webhook.fronesislabs.com/evaluate) which is not a known, verified compliance service, creating a potential data exfiltration risk. While the skill's stated purpose is policy enforcement, the external call is not justified within the skill's local logic and could transmit sensitive user data without adequate transparency or user consent.
Generated May 12, 2026
An AI-powered financial advisor generates investment recommendations. Use DCL Policy Enforcer to check outputs against finance policy (MiFID II/SEC/FCA) to prevent unqualified advice and ensure required disclaimers are present.
A healthcare chatbot provides general health information. Apply medical policy to block diagnostic claims or dosage guidance, ensuring outputs comply with HIPAA and EU MDR while directing users to professionals.
A customer service LLM is exposed to user prompts that try to override instructions. Use anti_jailbreak policy to detect prompt injection, DAN, or role-switch attempts, protecting the system from misuse.
An AI generates personalized marketing emails. Enforce GDPR policy to prevent unlawful data sharing, retention, or sale of personal data, ensuring compliance with data protection regulations.
An AI system generates content for EU users. Apply eu_ai_act policy to verify transparency, no impersonation, and no manipulation or social scoring, meeting regulatory requirements.
Offer tiered subscription plans for enterprises needing ongoing compliance checks for their AI outputs, with volume-based pricing on evaluations.
Charge per API call for each policy evaluation, suitable for smaller businesses or occasional use, with discounts for bulk pre-paid packages.
License the policy enforcer as a white-label module for integration into third-party AI platforms, charging a flat annual license fee plus per-evaluation royalty.
💬 Integration Tip
Start with a single policy (e.g., anti_jailbreak) using curl to test the endpoint, then integrate the API call into your LLM pipeline with the user's response as the input.
Scored Jul 8, 2026
Audited Apr 17, 2026 · audit v1.0
基于睿观的产品图片政策合规检测，通过视觉相似度匹配识别潜在违规商品。当用户提到政策合规检查、产品图片合规、违规检测、禁售商品筛查、基于图片的合规审查、上架前风险排查、policy compliance detection, product compliance review, violation detectio...
AI 合同风险审查服务。当用户需要审查合同、检查法律风险、分析合同条款、 审阅法律文书时使用本技能。覆盖违约责任、知识产权、付款条件、验收标准、 保密义务、管辖法院等15类法律风险。支持快速扫描和深度审查两档服务。 触发词：合同审查、审核合同、检查合同、法律风险、条款分析、法务审查、 合同风险、审合同、法律审查、...
产品图片的图形商标检测与相似度搜索。当用户提到商标检测、图形商标搜索、Logo侵权检查、商标相似度分析、图片商标风险评估、产品图片商标筛查、graphic trademark detection, logo infringement, trademark similarity, trademark risk, i...
面向电商产品Listing的文字商标检测与侵权风险分析。当用户提到商标检测、商标风险检查、品牌侵权筛查、产品标题商标扫描、文字商标查询、Listing合规检查、知识产权风险评估、text trademark detection, trademark infringement, brand infringement...
GDPR and German DSGVO compliance automation. Scans codebases for privacy risks, generates DPIA documentation, tracks data subject rights requests. Use for GD...
CAPA system management for medical device QMS. Covers root cause analysis, corrective action planning, effectiveness verification, and CAPA metrics. Use for...