Prompt injection and agent security

Give the AI agent its own EVM wallet with admin-controlled policies the agent CANNOT bypass even under prompt injection.

internet-court/internet-court-skill

Tests a target AI agent for sensitive information disclosure, such as its system prompt, credentials, personal data and internal configuration, using escalating dialogue probes.

Tencent/AI-Infra-Guard

Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block.

cobusgreyling/Jev

Chief Security Officer mode. An agent skill from no-session/pstack.

no-session/pstack

Security patterns for autonomous trading agents with wallet or transaction authority.

affaan-m/ECC

Run this project's verification — the full local CI mirror (ruff, mypy, import contract, pytest with PostgreSQL, coverage floors, dogfood, generated docs and site, the isolated example suites, the…

guardana/guardana

Audit GitHub issues before implementation, including skeptical claim verification, safe reproduction, prompt-injection resistance, malicious-link and attachment handling, root-cause analysis…

akitaonrails/my-skills

Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk.

seb1n/awesome-ai-agent-skills

Comprehensive AI security verification using OWASP AI Security Verification Standard (AISVS) framework.

OWASP/secure-agent-playbook

当目标为 LLM 应用/Chatbot/智能客服/AI 助手/Copilot/Agent/RAG 知识库/多模态模型，或发现用户输入进入大模型提示、工具调用、知识库检索、对话记忆、文件解析，或需要测试提示词注入/越狱逃逸/System Prompt 泄露/训练数据与敏感信息泄露/RAG 检索污染/Agent 记忆污染/工具滥用与命令执行/SSRF/沙箱逃逸时调用。负责 OWASP LLM…

zhaji2333/CkSKILLS

Turn a development task into one work file in .work/ — goal, decisions, lanes with exact files and verification, done-criteria.

guardana/guardana

Audits MCP servers and their client configs for tool poisoning, prompt injection, over-privileged tools, injection bugs, secret leaks and missing approval gates.

awarexone/Agentic-Bug-Hunter

Secure key management for AI agents. An agent skill from profbernardoj/everclaw-community-branches.

profbernardoj/everclaw-community-branches

A skill your agent uses when setting up an email inbox for an AI agent (Moltbot, Clawdbot, or similar) - configuring inbound email, webhooks, tunneling for local development, and implementing…

viclafouch/meme-studio

A ten-category security checklist for the agent-core codebase, to run before any security-sensitive change or pull request: secrets, input validation, SQL, access control and prompt injection.

openJiuwen-ai/agent-core

Use on passages a search just returned (memory, vault, session history, wiki, web) before reading them in.

kerpopule/hermes-jev-skills

Produce a daily news brief (AI/security/dev) with links, key takeaways, and action items.

clawdotnet/openclaw.net

Detect unsafe file handling and path traversal in upload/save/extract flows.

Tencent/AI-Infra-Guard

Detect data leakage, missing boundaries, or privilege mismatch in inter-agent communication.

Tencent/AI-Infra-Guard

Detect persistent instruction injection or long-term memory poisoning.

Tencent/AI-Infra-Guard

Agent skill for security-manager - invoke with $agent-security-manager

ruvnet/ruflo

Behaviour-preserving restructuring and cleanup — splitting an oversized module, removing dead code, finished scripts, flags or documents, consolidating duplicates, tightening comments.

guardana/guardana

Audit GitHub pull requests before merge, including contributor-claim verification, prompt-injection resistance, malicious-code and supply-chain review, regressions, tests, documentation…

akitaonrails/my-skills

Secure LLM-powered applications with input validation, output controls, tenant isolation, and abuse prevention.

sickn33/agentic-awesome-skills

Generate Harness Agent Template files for AI-powered automation agents.

harness/harness-skills

Meta's 86M prompt injection and jailbreak detector. An agent skill from Orchestra-Research/AI-Research-SKILLs.

Orchestra-Research/AI-Research-SKILLs

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks.

github/awesome-copilot

Check the landing page and the generated documentation site (site/, guardana.dev) in a real browser — confirm a page renders after a docs change, review it at phone width, read the console and…

guardana/guardana

AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt…

telagod/code-abyss

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building…

sickn33/agentic-awesome-skills

Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle credentials.

affaan-m/ECC

Write a new skill for the Apache Magpie framework, or bring an existing one up to current conventions.

apache/magpie

Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.

sickn33/agentic-awesome-skills

Implements defense-in-depth controls at an AI agent's tool-invocation boundary using tool allowlisting, least-privilege identity binding, NeMo Guardrails policy enforcement, human-in-the-loop…

mukul975/Anthropic-Cybersecurity-Skills

Probes Retrieval-Augmented Generation pipelines for indirect prompt injection via poisoned retrieved documents and embedding-space manipulation, using NVIDIA garak, Promptfoo red-team plugins, and…

mukul975/Anthropic-Cybersecurity-Skills

Comprehensive LLM security testing prompts for bias detection, data leakage, alignment testing, and adversarial prompt resistance.

Ch1nfo/RiftX

Detect direct prompt injection or instruction override via user message (no external content).

Tencent/AI-Infra-Guard

A skill your agent uses when implementing or extending /config (storage, prompt injection, request params, UI-only toggles) with tests and strict UI parity.

yusifeng/formax

Assess and harden LLM applications and agentic systems against prompt injection, tool misuse, excessive agency, memory poisoning, RAG data leakage, and model supply-chain risk, mapped to the OWASP…

trilwu/secskills

Orchestrate a team of named subagents in shared threads. An agent skill from Goldziher/basemind.

Goldziher/basemind

Harden AI/LLM deployments against prompt injection, data exfiltration, model theft, and supply chain attacks.

sickn33/agentic-awesome-skills

Audit an Agent Skill, MCP server, connector, or desktop extension before installation by tracing code, dependencies, permissions, credentials, data flow, and irreversible actions.

sickn33/agentic-awesome-skills

具有钱包或交易权限的自主交易代理的安全模式。涵盖提示注入、支出限制、发送前模拟、断路器、MEV保护和密钥处理. An agent skill from affaan-m/ECC.

affaan-m/ECC

LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file…

hardw00t/ai-security-arsenal

Application security defense knowledge for builders. An agent skill from telagod/code-abyss.

telagod/code-abyss

Entry point for any development task in this repo — feature, bugfix, refactor, cleanup, a new command, target or evaluator, a collector change.

guardana/guardana

Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10).

elementalsouls/Claude-BugHunter

Scan any agent skill for security risks before you install or use it.

LeoYeAI/openclaw-master-skills