Search
“MCP and agent security”
Showing 1–24 of 1,261 for “MCP and agent security”
- 0.734score
Agent Security Scanner MCP
sinewaveai
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
ConnectorBFreshness: BLocal★ 124Claude Code +5 - 0.493score
AgentSecurityLens MCP Security Trust Check
professor2k8
MCP security trust-check for agents before installing MCPs, Skills or tools.
ConnectorCFreshness: CLocalClaude Code +5 - 0.536score
mcp-security
ils15
MCP security hardening — credential leakage prevention, input sanitization, and tool access control.
SkillCFreshness: C★ 12Claude Code +9 - 0.574score
ai-mcp-security
Wang200935
AI 与 MCP 安全评估 — Prompt 注入、工具滥用、MCP 信任边界、Agent 权限逃逸、数据泄露、模型风险、GAARM 风险矩阵。Use when testing LLM-based applications, MCP servers, agent orchestration systems, AI…
SkillBFreshness: B★ 4Claude Code +9 - 0.875score
ai-agent-security
devops-skills
Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.
SkillAFreshness: A★ 48.4KClaude Code +9 - 0.782score
Shellward
jnMetaCode
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
ConnectorAFreshness: ALocal★ 139Claude Code +5 - 0.420score
Agent Security
mdfifty50-boop
Security scanning and threat detection for AI agents
ConnectorDFreshness: DLocalClaude Code +5 - 0.554score
mcp-security
NetVar1337
MCP (Model Context Protocol) 协议安全测试方法论。当目标环境使用 MCP Server 集成外部工具、 需要评估 MCP 工具描述安全性、或测试 Agent 通过 MCP 调用工具时的安全边界时触发。 覆盖: 工具描述投毒、地毯式骗局(动态篡改)、指令覆盖(Shadow…
SkillBFreshness: B★ 2Claude Code +9 - 0.538score
Vibes-Coded Agent Security and Commerce Tools
doteyeso-ops
Agent supply-chain security, scanner consensus, x402 reliability, and commerce MCP tools.
ConnectorAFreshness: ARemote★ 3Claude Code +3 - 0.586score
Helixar Security
helixar.aiOfficial
Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.
ConnectorAFreshness: ARemoteRead-onlyClaude Code +3 - 0.531score
Securityscan
securityscan-api
Security for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout.
ConnectorBFreshness: BLocal↓ 25/wkClaude Code +5 - 0.515score
Agent Security Scanner
Mikehzp
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
ConnectorCFreshness: CLocal↓ 57/wkClaude Code +5 - 0.453score
mcp-security
omer-metin
Security patterns for MCP servers including OAuth 2.0, rate limiting, input validation, and audit loggingUse when "mcp security, mcp authentication, mcp…
SkillDFreshness: D★ 180Claude Code +9 - 0.538score
MCP Audit Server
joepangallo
Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend
ConnectorBFreshness: BLocalClaude Code +5 - 0.483score
Agentic Security Shield
ormuzdo
12-layer security configs for AI coding agents.
ConnectorCFreshness: CRemoteDownClaude Code +3 - 0.554score
agent-security
NetVar1337
AI Agent 系统安全测试方法论。当目标系统使用 AI Agent 执行工具调用、多 Agent 协作、 或自主决策时触发。覆盖 OWASP Agentic AI Security Top 10 (ASI01-ASI10): 目标劫持、工具滥用、身份权限、供应链、代码执行、记忆投毒、多 Agent 通信、…
SkillBFreshness: B★ 2Claude Code +9 - 0.704score
agent-security-auditor
shannhk
Use when auditing a VPS-based Hermes agent setup for exposed dashboards, weak secret handling, broad keys, Docker risks, or missing backup/security…
SkillCFreshness: C★ 732Claude Code +9 - 0.640score
setup-security-agent
awsOfficial
Configure AWS Security Agent for the current workspace — provision or reuse an agent space, IAM service role, and S3 bucket.
SkillBFreshness: B★ 3KClaude Code +9 - 0.476score
Gsep MCP
gsepcore
AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.
ConnectorCFreshness: CLocal↓ 19/wkClaude Code +5 - 0.878score
security-advisory
modelcontextprotocolOfficial
Take a privately reported vulnerability through this repo's security advisory flow: board it as a draft card, check whether the code is this repo's server or…
SkillAFreshness: A★ 91.5KClaude Code +9 - 0.581score
ai-security-agent
hellodqy
AI/LLM security reasoning agent.
SkillBFreshness: B★ 14Claude Code +9 - 0.828score
security-audit
cloudflareOfficial
Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons.
SkillBFreshness: B★ 43.8KClaude Code +9 - 0.827score
security-model
getsentryOfficial
Define, review, or update SECURITY_MODEL.md files that tell security review tools a repository's threat model, trust boundaries, invariants, reportable…
SkillAFreshness: A★ 1.1KClaude Code +9 - 0.740score
fisc-to-aws-security-agent
aws-jp-fsi-saOfficial
Deterministically generates source documents (Markdown) from the FISC "Security Guidelines on Computer Systems for Financial Institutions" (安対基準 / Antai…
SkillAFreshness: A★ 15Claude Code +9