MCP App StoreMCP App Store
from anti-distillation-skill22
Generate targeted "pollution" content and personas to reduce the risk of being distilled into reusable AI models; helps individuals inject subtle or aggressive
This skill helps individuals produce structured "pollution" content (persona configs, trap snippets, and execution plans) from personal data sources (chat logs, Git commits, documents) to make automated model distillation less reliable. It guides intake, selects a pollution mode (subtle/aggressive/chaos), and outputs actionable files intended for manual use.
Use when you want to protect your personal knowledge and communication style from being copied into organizational models — for example before leaving a job, when exporting chat logs or repos, or when you want to introduce ambiguity into public artifacts. Not for automated modifications of company data; outputs are manual suggestions.
Likely usable by general-purpose chat/coding agents that can run Bash and file Read/Write tools; compatible with agents that support prompts and file operations (e.g., Copilot-style assistants, Claude/ChatGPT integrations).
Anti-distillation skill that generates deceptive 'pollution' personas and trap content to prevent AI model distillation of an individual's work style. SKILL.md is well-structured and bilingual (Chinese/English) with clear 3-step workflow, but contains no executable scripts — all tools are prompt instructions for the agent. References directories (prompts/, tools/) that aren't bundled. Ethically questionable purpose (generating misleading content) but no direct security threats.
The skill's core purpose is generating deceptive content to poison AI training data. While the SKILL.md includes disclaimers about legal use, the functional design is built around misleading others. No technical security issues found — no exfiltration, no phone-home, no destructive commands. The skill is entirely prompt-based with no executable code.
Cashu Wallet
Privacy-focused Bitcoin wallet skill enabling sending/receiving via Lightning and Cashu ecash tokens, with multi-mint support and basic wallet management comman
CLS-Certify — Skill Security Auditor
Enterprise-grade multi-dimensional security scanner for Agent Skills that produces S+/S/A/B/C/D ratings and structured HTML/PDF reports.
Speak Security Basics
Security best practices for integrating Speak: API key management, audio data privacy, student data protection, and COPPA/FERPA compliance for production deploy
Configure Nightwatch
Practical guidance to configure Laravel Nightwatch: sampling, filtering, and redaction to balance observability, performance, and privacy.
Hypertension Management Assistant
Record and assess blood pressure readings, provide day‑of trend analysis, recommend relaxation/audio therapy, and generate single‑day health reports while prior
MUAPI Photo Pack Generator (Identity-Lock)
Generate themed photo packs from a single reference image while preserving the exact facial identity and enforcing identity-lock guardrails.
Zero-Knowledge Proofs (Stellar/Soroban)
Guidance and patterns for integrating zero-knowledge proofs and privacy-preserving primitives into Stellar/Soroban smart contracts.
OSINT Investigator
Comprehensive OSINT playbook for agents: generates dorks, runs recon, builds timelines, analyzes metadata, and produces structured intelligence reports while re