PyPI · crates.io · npm
hashgraph-online/hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Apache-2.02026年10月22日 · 指标 2.10.0
全部标签
目录标签
#prompt-injection
公开记录中带有此标签的全部仓库——标签来自其 GitHub 主题或软件包注册表发布的关键词。健康度量遵循与记录其余部分相同的版本化方法论。
77 条记录
npm · PyPI
NVIDIA/SkillSpector
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
Apache-2.02026年9月19日 · 指标 2.10.0
PyPI · npm
NuGuardAI/nuguard
AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.
自定义许可证2026年9月10日 · 指标 2.10.0
npm
arcjet/arcjet-js
Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.
Apache-2.02026年9月11日 · 指标 2.10.0
PyPI
cisco-ai-defense/skill-scanner
Security Scanner for Agent Skills
自定义许可证2026年9月17日 · 指标 2.10.0
PyPI · crates.io
duriantaco/skylos
Open source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistakes before merge. For first timers refer to https://duriantaco.github.io/skylos/repo-map/
Apache-2.02026年9月15日 · 指标 2.10.0
PyPI · RubyGems
OWASP/www-project-agent-memory-guard
OWASP Foundation web repository
Apache-2.02026年8月25日 · 指标 2.10.0
npm
node9-ai/node9-proxy
The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.
Apache-2.02026年9月13日 · 指标 2.10.0
npm
asamassekou10/ship-safe
CLI security scanner built for the agentic era. Detects CI/CD misconfigs, agent permission risks, MCP tool injection, hardcoded secrets, and DMCA-flagged AI dependencies.
MIT2026年9月6日 · 指标 2.10.0
npm · PyPI
Agent-Threat-Rule/agent-threat-rules
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable rules across 10 categories; merged into Microsoft AGT, Cisco AI Defense, MISP, OWASP, FINOS & SigmaHQ. MIT-licensed.
MIT2026年9月9日 · 指标 2.10.0
Go
cfgaudit/cfgaudit
Static security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. 109 rules, SARIF output, OWASP LLM Top 10 mapping.
Apache-2.02026年10月20日 · 指标 2.10.0
npm · PyPI
issdandavis/SCBE-AETHERMOORE
Geometric AI governance and evaluation framework with a 14-layer security pipeline, semantic projection, and reproducible benchmark lanes.
MIT2026年8月26日 · 指标 2.10.0
PyPI · npm
PrismorSec/prismor
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
Apache-2.02026年9月11日 · 指标 2.10.0
Go
peg/rampart
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.
Apache-2.02026年9月6日 · 指标 2.10.0
npm
lua-ai-global/governance
Zero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)
MIT2026年9月13日 · 指标 2.10.0
Go
openclaw/clawscan
Composable security scanning harness for agent skills
MIT2026年9月13日 · 指标 2.10.0
PyPI
pezhik/skilltotal
Scan AI components (MCP servers, agent skills, npm/PyPI packages) for malware & risky capabilities. Local, deterministic, evidence-anchored. Free & OSS.
Apache-2.02026年10月9日 · 指标 2.10.0
npm
getmcpm/cli
MCP security guard + package manager. Block prompt injection, tool poisoning and rug-pulls in Model Context Protocol servers at runtime; trust-scored installs with Sigstore provenance for Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and Gemini CLI. Local, deterministic, no LLM in the loop.
MIT2026年9月8日 · 指标 2.10.0
npm · PyPI
sinewaveai/agent-security-scanner-mcp
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.
MIT2026年10月9日 · 指标 2.10.0
PyPI · npm
QWED-AI/qwed-open-responses
Verification guards for OpenAI Responses API - Verify AI agent outputs before execution
Apache-2.02026年9月18日 · 指标 2.10.0
Go · PyPI
luisgf/infrabroker
Infrastructure access broker for AI agents — SSH & Kubernetes. Per-operation ephemeral credentials minted by a separate signer; the model never touches one. MCP stdio / HTTP+OIDC.
GPL-3.02026年9月19日 · 指标 2.10.0
Packagist
promptphp/intercept
A modular, drop-in middleware collection for Laravel AI SDK agents. Offers middleware across security, observability, performance and guidance.
MIT2026年9月26日 · 指标 2.10.0
PyPI · npm
AlexanderMattTurner/agent-sanitizer
Strip common prompt injection surfaces.
Apache-2.02026年10月22日 · 指标 2.10.0
npm
Drakon-Systems-Ltd/ShieldCortex
Memory security for AI agents. Scan native memory writes, gate tools on bound hosts, inspect what was stored. Not a second brain.
MIT2026年10月20日 · 指标 2.10.0
PyPI
crucible-security/crucible
pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents
Apache-2.02026年9月10日 · 指标 2.10.0
PyPI · npm
gautamvarmadatla/mcpsafetywarden
MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP server, profiling tool behavior, blocking destructive calls, and running active security audits before you trust them in a workflow.
自定义许可证2026年9月15日 · 指标 2.10.0
npm
panguard-ai/panguard-ai
Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent 開源安全平台 -- 安裝前審計 skill、24/7 即時監控、社群共享威脅情報。
MIT2026年10月22日 · 指标 2.10.0
npm
superagent-ai/superagent
Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.
MIT2026年9月20日 · 指标 2.10.0
Go
themayursinha/mcp-visor
Runtime policy enforcement and audit control plane for MCP tool execution. Deterministic, non-AI policy engine that intercepts MCP tools/call requests before execution.
MIT2026年10月18日 · 指标 2.10.0
npm
BlackUnicornSecurity/bonklm
BonkLM - LLM Security Guardrails with Interactive Setup Wizard
Apache-2.02026年9月18日 · 指标 2.10.0