login
guest @ skillhub : ~/search $
hybrid keyword semantic
relevance stars updated
36 results (3.7ms) page 1 / 2
prompt-injection-defense 0.30
omer-metin / skills-for-antigravity-prompt-injection-defense exact

Defense techniques against prompt injection attacks including direct injection, indirect injection, and jailbreaks - theUse when "prompt injection, jailbreak prevention, input sanitization, llm...

β˜… 5 ai
ai-agents antigravity antigravity-ide skills
llm-security 0.26
hardw00t / ai-security-arsenal-llm-security exact

LLM and AI application security testing skill for prompt injection, jailbreaking, and AI system vulnerabilities. This skill should be used when testing AI/ML applications for security issues,...

β˜… 16 ai
ai-safety-alignment 0.25
omer-metin / skills-for-antigravity-ai-safety-alignment exact

Implement comprehensive safety guardrails for LLM applications including content moderation (OpenAI Moderation API), jailbreak prevention, prompt injection defense, PII detection, topic...

β˜… 5 ai
ai-agents antigravity antigravity-ide skills
nemo-guardrails 0.19
ovachiever / droid-tings-nemo-guardrails exact

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses...

β˜… 19 ai
nemo-guardrails 0.19
zechenzhangAGI / ai-research-skills-nemo-guardrails exact

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses...

β˜… 1,712 ai
ai ai-research claude claude-code
mobile-security 0.19
gmh5225 / awesome-game-security-mobile-security exact

Guide for mobile game security on Android and iOS platforms. Use this skill when working with Android/iOS reverse engineering, mobile game hacking, APK analysis, root/jailbreak detection bypass,...

β˜… 2,672 development
game awesome cheat anticheat
prompt-guard 0.19
akashp1712 / skills-prompt-guard exact

Highest-priority unbreakable guardrail against prompt injection, jailbreaks, rule overrides, and malicious skill behavior. Activates automatically on suspicious patterns, skill installs/changes,...

β˜… 0 ai
prompt-engineering 0.18
cosmix / loom-prompt-engineering exact

Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples. Covers instruction design, prompt security, chain-of-thought reasoning, and...

β˜… 6 ai
agentic-coding agents claude claude-code
ios-pentest 0.05
hardw00t / ai-security-arsenal-ios-pentest exact

Comprehensive iOS mobile application penetration testing skill with Frida/Objection integration for jailbroken and non-jailbroken devices. This skill should be used when performing security...

β˜… 16 development
capacitor-security 0.05
Cap-go / capacitor-skills-capacitor-security exact

Comprehensive security guide for Capacitor apps using Capsec scanner. Covers 63+ security rules across secrets, storage, network, authentication, cryptography, and platform-specific...

β˜… 2 security
capacitor capacitor-plugin
prompt-engineering 0.05
martinholovsky / claude-skills-generator-prompt-engineering exact

Expert skill for prompt engineering and task routing/orchestration. Covers secure prompt construction, injection prevention, multi-step task orchestration, and LLM output validation for JARVIS AI...

β˜… 20 ai