Prompt injection and agent security

Decides whether an agent skill is safe to install by combining a SkillSpector static scan with the agent's own source review, ending in APPROVE, CAUTION or REJECT.

NVIDIA/SkillSpector

Scan agent skills for security issues. An agent skill from getsentry/skills.

getsentry/skills

Query AI Safety HOT news, research papers, incidents, hot topics, and daily/weekly/monthly reports through its public read-only MCP service.

wuyoscar/AISafetyHot-Hub

Probes an AI agent through dialogue for cross-user data access, privilege escalation and login bypass, and reports confirmed findings as structured vulnerability entries.

Tencent/AI-Infra-Guard

Cross-agent self-inspection of your AI-agent stack. An agent skill from alexgreensh/repo-forensics.

alexgreensh/repo-forensics

Run HOL Guard scanner and guard operations via uv run hol-guard.

hashgraph-online/hol-guard

Investigate and harden Skylos security behavior. An agent skill from duriantaco/skylos.

duriantaco/skylos

Run a pre-deployment security compliance checklist based on KISA guidelines.

cdppcorp/KESE-KIT

Install or initialize HOL Guard local runtime protection for Claude Code.

hashgraph-online/hol-guard

Comprehensive security review framework for AI agents. An agent skill from slowmist/slowmist-agent-security.

slowmist/slowmist-agent-security

Applies the AI SAFE2 framework to security reviews, code reviews and compliance mapping for AI agents, RAG pipelines and MCP servers.

CyberStrategyInstitute/ai-safe2-framework

按中国法规（网安法 / PIPL / 等保2.0 / 数据出境 / AI生成内容标识）审计一个 AI 项目的代码仓库，产出每条都带 文件:行 取证、经独立复核、经脚本校验的合规报告。当用户问「这个项目上线合不合规」「调用了 OpenAI/Claude 算不算数据出境」「要不要做 AI 标识」「帮我做合规自查/等保/PIPL 检查」时使用。Audit an AI project's…

jnMetaCode/shellward

Apply the SAIL (Secure AI Lifecycle) V2 framework by Pillar Security to secure AI applications and agents.

pillar-labs/sail-skill

Installs hooks that check each agent action against security policies before it runs, blocking destructive commands and logging every decision.

pegasi-ai/reins

Probes an AI agent through dialogue to check whether its file, code-execution or network tools can be misused to run unexpected code or reach outside targets.

Tencent/AI-Infra-Guard

A skill your agent uses when running or explaining the ClawScan CLI, including one-off agent-skill scans, benchmark runs, scanner fixtures, judge harness commands, env var validation, and…

openclaw/clawscan

Guide for writing eval conversation JSONs and running them through policy engines

open-bias/open-bias

Tells a model how to treat the tagged double-brace placeholders that Maskit's local privacy gateway substitutes for sensitive text, so tokens are copied exactly instead of guessed, split or faked.

xiaYuTian11/maskit

Commit and push a finished change the way this repo requires — explicit paths, one commit per logical change, no attribution, the five documentation places answered, the site checks before a push (a…

guardana/guardana

Native Rust browser automation CLI for AI agents. An agent skill from gsd-build/gsd-browser.

gsd-build/gsd-browser

Auto-fix security vulnerabilities found in CII, AI, robot, space, and supply chain systems.

cdppcorp/KESE-KIT

Check HOL Guard local protection status for Claude Code without changing configuration.

hashgraph-online/hol-guard

Statically audits GitHub Actions workflows that run AI coding agents, tracing attacker-controlled input to agent prompts and flagging unsafe sandbox, trigger and allowlist settings.

trailofbits/skills

Probes whether an agent with web fetch and stored user memory can be tricked by a malicious page into leaking data through chained URL paths.

Tencent/AI-Infra-Guard

A skill your agent uses when a researcher, maintainer, or contributor found or suspects a malicious skill on ClawHub and needs a private reporting workflow: opening a GitHub private vulnerability…

openclaw/clawscan

Probes whether an agent can be hijacked by instructions hidden in documents, retrieved chunks or fetched web pages, using test prompts that embed a hidden instruction.

Tencent/AI-Infra-Guard

Security hardening toolkit for OpenClaw. An agent skill from adversa-ai/secureclaw.

adversa-ai/secureclaw

A skill your agent uses when an OpenClaw maintainer or owner is reviewing a ClawHub malicious-skill profile proposal PR: checking proposals/<GHSA-ID/clawscan.yml, reading the private vulnerability…

openclaw/clawscan

Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings.

seb1n/awesome-ai-agent-skills

Add security coverage to Guardana the way this repository requires — as a rule, evaluator or target, never by patching the engine — with the fixtures, the framework mapping and the documentation…

guardana/guardana

Generate secure coding prompts and guides for AI tools (Claude, ChatGPT, Cursor, Copilot).

cdppcorp/KESE-KIT

Use HOL Guard to preview and protect AI-agent package installs, Cursor surfaces, CI, and automation workflows.

hashgraph-online/hol-guard

Static safety audit of a SKILL.md that scores five dimensions and acts as a gate: skills below the pass line do not ship, whatever else they score.

openJiuwen-ai/agent-core

Finds security threats in a design with a STRIDE pass per component, rates severity and records fixes, with extra checks for AI agent and tool risks.

dralgorhythm/claude-agentic-framework

Applies the AI SAFE2 v3.1 governance framework to designing, building, auditing and testing AI agents, RAG pipelines, MCP and tool integrations and AI infrastructure.

CyberStrategyInstitute/ai-safe2-framework

Autonomous, non-interactive run of the whole lifecycle for one development task — size, plan, build, gate, review, fix, commit — without stopping for questions.

guardana/guardana

Refreshes the guide's coding-agent and MCP security threat data through AgentSec Triage: research advisories, add tested records and synchronize the public feed.

FlorianBruniaux/claude-code-ultimate-guide

Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them.

iflytek/skillhub

Documentation work in this repo — the five places a user-visible change must answer, the page conventions the site build enforces, the tests that pin prose to the registry, and a simplification pass…

guardana/guardana

Run a security vulnerability assessment based on KISA guidelines.

cdppcorp/KESE-KIT

Report/investigate RUNTIME ACTIVITY of AI agents (Agent 365 / Copilot Studio / M365 Copilot / Work IQ) — agents used, tools/connectors, channels, tokens, prompt/reply content, and Prompt Shield…

SCStelz/security-investigator

OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation

jnMetaCode/shellward

Detect error propagation, chain failures, and single-point breakdowns that cascade across agent workflows.

Tencent/AI-Infra-Guard

AI governance, EU AI Act compliance, OWASP LLM security, responsible AI practices for GitHub Copilot agents

Hack23/cia

Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and missing guardrails.

OWASP/secure-agent-playbook

A skill your agent uses when reviewing an agent Skill before sharing, installing, or executing it and when checking a Skill bundle for credentials, dangerous commands, suspicious network behavior…

zrt-ai-lab/opencode-skills

Hunt for the failure this project exists to prevent — code that compiles, types, tests green, and quietly reports "all clear" about something it never examined.

guardana/guardana

Audit or report on AI agent security posture across Copilot Studio, Microsoft 365 Copilot, Microsoft Foundry, and third-party agents.

SCStelz/security-investigator