Personhood verification and Sybil resistance for 0xagentprivacy. Activates when discussing ∃! (unique existence) binding, proof-of-personhood without identity disclosure, Sybil…
Standards and policy governance for 0xagentprivacy. Activates when discussing IEEE 7012, BGIN working groups, Internet Identity Workshop, Trust Over IP Foundation, W3C…
Dark Forest Navigator for 0xagentprivacy. Activates for dark forest strategy, privacy-preserving path optimisation, minimum-exposure routing, cross-chain navigation under…
Reputation and credential evolution (SBT→VRC) for 0xagentprivacy. Activates when discussing soulbound tokens, verifiable credentials, credential lifecycle, reputation staking,…
Infrastructure Security Architect for 0xagentprivacy. Activates for TEE monitoring, separation matrix enforcement, infrastructure health checks, cross-chain bridge security, agent…
Adversarial Researcher (red team) for 0xagentprivacy. Activates when testing privacy architectures for weaknesses, running attack simulations, stress-testing separation bounds,…
Tetrahedral sovereignty model and 4×4 separation matrix for 0xagentprivacy. Activates when discussing Φ(Σ), det(Σ), the four forces (Protect, Project, Reflect, Connect),…
Threat modelling and adversarial analysis for 0xagentprivacy. Activates when discussing R(d) adversarial bounds, attack surface analysis, red team methodologies, trusted setup…
Use when adding capabilities to an existing agent project — memory, app integration, VPC, multi-agent, migration, model changes, browser, code interpreter, or resource removal.
Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies.
Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input…
AI agent configuration security scanner — 102 rules across secrets, permissions, hooks, MCP servers, and agent definitions.
AI agent memory backup. Register at agentsmem.com, get an API key, then encrypt and upload memory via the API; owner manages backups on the web.
List all secrets. Requires authentication. Use for Agentuity cloud platform operations
Pull secrets from cloud to local .env file. Requires authentication. Use for Agentuity cloud platform operations
Push secrets from local .env file to cloud. Requires authentication. Use for Agentuity cloud platform operations — from security/security-misc
Author, edit, and lint `governance:` blocks in `*.eval.yaml` files. Use when creating or updating evaluation suites that carry AI-governance metadata (OWASP LLM Top 10, OWASP…
Get AI ecosystem intelligence from AgentWyre. Use when you need to check for breaking changes, security vulnerabilities, new model releases, or pricing updates across the AI…
Aggregate breaking cryptocurrency news from 50+ sources including CoinDesk, CoinTelegraph, The Block, and Decrypt.
Cross-agent messaging via SQLite. Send messages between Claude Code, Codex, Gemini CLI, and other agents. No daemon, no network, no dependencies beyond bash and sqlite3.
Author-guideline skill for Agriculture & Food Security (BMC / Springer Nature, open access). Use to format or check a manuscript for this BMC journal — structure, mandatory BMC…
Author-guideline skill for Q1/Q2 agriculture journals from society, academy, and regional publishers not covered by a dedicated publisher skill: Soil (Copernicus), Plant Soil and…
Provides sandboxing validation, HMAC key rotation, and budget verification to manage security boundaries under Agentic Group Theory (AGT).
Use when red-teaming an agentic AI / LLM application — indirect & zero-click prompt injection, MCP tool poisoning, persistent memory poisoning, excessive-agency tool abuse,…
Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.
Verify external, vendor, and third-party claims (numbers, attributions, structure) against authoritative primary sources before they land in a repo artifact or external…
Použij, když máš nastavit, synchronizovat nebo diagnostikovat AI agnostické prostředí repozitáře sdílené mezi Claude Code, Cursor a GitHub Copilot – třeba u proseb „nastav agenty…
AI自動化工作流設計技能 - 幫中小企業設計自動化流程、選擇工具、搭建n8n/Zapier工作流。適合AI Automation Agency、顧問、企業主。觸發詞：自動化、工作流、n8n、Zapier、automation、workflow、流程優化、AI agent。
Transform any AI into a professional executive assistant with battle-tested personas and workflows. Complete templates for Google Workspace integration (Gmail, Calendar, Drive),…
Security vulnerabilities in AI-generated code and LLM applications, covering OWASP Top 10 for LLMs, secure coding patterns, and AI-specific threat modelsUse when "ai code…
Use when explicitly asked to audit or synchronize Claude and Codex rules, skills, hooks, plugins, credentials, or shared
memory.
Provides AI consultation workflows, prompt templates, and best practices for multi-model consultation.
Dual-AI code validation using both Claude and Google Gemini to catch 20% more issues. Validates React Native screens for security vulnerabilities, performance anti-patterns,…
AI 系统数据安全测试方法论。当需要评估 LLM/AI 系统的数据泄露风险、训练数据安全、 或 RAG/向量库数据完整性时触发。覆盖: System Prompt 泄露(元 Prompt/角色扮演/关键字定位)、 训练数据推导与提取、成员推断攻击、模型反演攻击、RAG 数据投毒、API 信息泄露、 级联幻觉攻击、外部数据源信息泄露。
AI-augmented development controls, GitHub Copilot governance, LLM security, AI-generated code review per Hack23 Secure Development Policy
Pijplijn voor het bijsturen van AI-GEDRAG in TriFinity — hoe De Wil (en Kern/Horizon) praat, redeneert, categoriseert en antwoordt.
AI and LLM security testing — prompt injection, model manipulation, data exfiltration via AI. Use when testing
Generate PNG images using AI (multiple models via OpenRouter including Gemini, FLUX.2, Riverflow, SeedDream, GPT-5 Image, GPT-5.4 Image 2, proxied through Cloudflare AI Gateway…
GitHub, Anthropic blog ve topluluk kaynaklarını tarayarak yeni Claude skill/MCP/tool keşfeder. REPO_CATALOG.md'ye ekler, /ai-upgrade'e hazır hale getirir.
Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards).
Use for AI/LLM security assessments, prompt injection, RAG security, agent/tool permissioning, model supply chain, LLM red teaming, AI governance, eval design, data leakage,…
Production MLOps and ML/LLM/agent security skill for deploying and operating ML systems in production (registry + CI/CD, serving, monitoring/drift, evaluation loops, incident…
Conducts privacy auditing of AI models including training data extraction testing, membership inference attacks, model inversion testing, and attribute inference assessment.
Fetches AI & tech news (default) or any custom topic (crypto, geopolitics, etc.) from RSS feeds, Tavily search, Twitter/X, and YouTube.
Multi-AI engineering loop orchestrating Claude, Codex, and Gemini for comprehensive validation. USE WHEN (1) mission-critical features requiring multi-perspective validation, (2)…
Use to critically review AI-generated output (plans, code, docs, decisions) for the failure modes AI agents are prone to — unsupported assumptions, invented facts, conflicting…
write an article on cybersecurity, we will first prompt the model to generate some facts, types, or techniques for cybersecurity
Use when identifying AI-specific regulations and compliance requirements that apply to AI/ML-powered software products.
Identifying, assessing, and mitigating risks in AI systems including bias, safety, privacy, security, and ethical concerns.
Identify and defend against AI-powered scams including deepfakes, voice cloning, AI phishing, and fake job offers.
AI SDLC security testing workflow. Use when an AI assistant is asked for OWASP review, security testing, abuse-case analysis, authz/authn review, input validation review, secret…
Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse.
Enterprise AI security - OWASP LLM Top 10, prompt injection defense, guardrails, PII protection
AI Agent 安全检测工具。扫描 OpenClaw 等 AI Agent 的安全风险，包括 API Key 泄露、Skill 投毒、敏感信息泄露、配置风险等。当用户询问 AI 安全、Agent 安全、API Key 泄露、Skill 风险、安全扫描、安全审计时触发。
Evaluate AI solutions across 4 dimensions — Confidence, Risk, Effort, Soundness — before accepting any recommendation. Prevents blind plan acceptance and production disasters.
General AI Supply Chain Security Skill for any AI agent platform in 2026. Detects the exact class of attack that hit Vercel (and every similar real threat): over-privileged…
MANDATORY verification system that prevents Claude Code instances from making false claims or fabricating evidence.
MANDATORY verification system that prevents Claude Code instances from making false claims or fabricating evidence.
All-in-one academic research với 28 tools. Kết nối arXiv, PubMed, Semantic Scholar, bioRxiv, medRxiv, Google Scholar. Hỗ trợ auto-cite và AI scientific figure generation.
Security rule for timing-safe secret comparison. Use SHA3-256 hashing instead of timing-safe compare functions.