PyPI
HeadyZhang/agent-audit
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.
MIT2026年9月18日 · 指标 2.10.0
全部标签
目录标签
#llm-security
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。
88 条记录
PyPI
philpaz/recusal
Deterministic governance for Claude and MCP tool calls. Pin approved capabilities, detect drift, and refuse unsafe or unapproved actions before execution. No model in the decision path.
Apache-2.02026年9月14日 · 指标 2.10.0
PyPI
vishnu-77/secchecker
Static security scanner for AI agents, MCP tools, and LLM applications. Detects OWASP LLM Top 10 risks, unsafe tool use, prompt injection paths, secrets, and AI infrastructure misconfigurations. Zero runtime dependencies.
MIT2026年9月12日 · 指标 2.10.0
PyPI
veldtlabs/veldt-kya
Runtime control, security, and governance for AI agents — decide what an agent may do at the moment it acts, revoke that authority instantly, and keep tamper-evident evidence of every decision.
自定义许可证2026年9月8日 · 指标 2.10.0
PyPI
yunaremaia/taintrace
Typosquat detector for AI coding agent dependencies
MIT2026年10月4日 · 指标 2.10.0
npm
hawonb711-tech/nexus
Local-first trust layer for AI coding agents: structural prompt-injection and action guards, secret scanning, semantic memory, code review, and 17 MCP tools. No model API required.
MIT2026年9月21日 · 指标 2.10.0
Maven · PyPI
AindriuB/data-prism
Data Prism is an open-source privacy layer for Java/Spring teams putting LLM agents or MCP clients in front of internal APIs holding customer data. It pseudonymises personal data per privacy scope, refuses anything unclassified, and can keep a hash-chained audit trail.
Apache-2.02026年10月19日 · 指标 2.10.0
npm
Silmaril-Security/sdk-typescript
TypeScript SDK for Silmaril Firewall
自定义许可证2026年9月11日 · 指标 2.10.0
npm
flare-collection/flare-redact
Zero-dependency TypeScript secret and PII redaction for any SDK, logs, HTTP, LLM prompts, and scoped MCP tool boundaries.
MIT2026年9月18日 · 指标 2.10.0
Go
skilltrust/skill-detector
CLI to spot risky AI skill packages before you use them. Scans for injection, exfiltration, supply chain, and other threats.
MIT2026年10月19日 · 指标 2.10.0
npm · PyPI
stylusnexus/agent-armor
Open-source agent security framework. Detects and defends against AI Agent Traps — content injection, embedded jailbreaks, RAG poisoning, data exfiltration, and more. Based on the DeepMind Agent Traps taxonomy.
MIT2026年9月18日 · 指标 2.10.0
npm
subodhkc/ai-appsec
Evidence-backed AppSec for AI applications and agents. Powered by HAIEC.
MIT2026年9月20日 · 指标 2.10.0
PyPI
batrapulkit/squidbrake
Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.
Apache-2.02026年10月9日 · 指标 2.10.0
crates.io
kahramanemir/Vallum
Security boundary CLI proxy between AI coding agents and your shell — redacts secrets, neutralizes prompt injection, wraps untrusted terminal output, and audits every command. Single Rust binary.
Apache-2.02026年9月6日 · 指标 2.10.0
npm
putervision/spc
High-performance zero-dependency static analysis tool enforcing NASA Power of Ten rules across 20 programming languages, plus AI agent skill, MCP server config, prompt template, and LLM model security auditing.
MIT2026年9月18日 · 指标 2.10.0
npm
Synapsor/Synapsor-Runner
Let AI agents query and update Postgres/MySQL without raw SQL, unrestricted schema access, or database credentials in the model; writes stay reviewed.
Apache-2.02026年10月20日 · 指标 2.10.0
PyPI
ivegotahunnitonit/bartholomew
security
MIT2026年9月27日 · 指标 2.10.0
PyPI
Silmaril-Security/sdk-python
Python SDK for Silmaril Firewall prompt injection and jailbreak detection
自定义许可证2026年9月12日 · 指标 2.10.0
PyPI
aggrete/aggrete
该仓库未发布描述。
Apache-2.02026年10月11日 · 指标 2.10.0
Go
SVGreg/surfaceguard
Know what you're letting in — scans, signs and verifies what an agent loads. Agent Skills vs the OWASP Agentic Skills Top 10, with SARIF output and a load-time gate.
Apache-2.02026年9月14日 · 指标 2.10.0
npm
declaw-ai/declaw-js
TypeScript SDK for Declaw — security-first sandboxing for AI agents
Apache-2.02026年9月18日 · 指标 2.10.0
npm
theRizwan/llm-guard
A TypeScript library for validating and securing LLM prompts — PII, jailbreak, prompt injection, profanity, toxicity and relevance guards. Zero-config defaults, extensible with custom patterns.
MIT2026年9月7日 · 指标 2.10.0
npm
iAMv1/omnisectester
Nation-state grade, defense-in-depth security testing framework. Tests web apps, extensions, desktop, mobile, cloud, AI/LLM, hardware, and supply chain from a single CLI.
MIT2026年9月22日 · 指标 2.10.0
—
GoldenWing-360/claude-security-skills
25 production-tested defensive security skills for Claude Code - WordPress, VPS, Cloudflare, Next.js hardening, AI agent guardrails, MCP security, prompt injection defense, OWASP LLM Top 10, LLM coding failure modes (slopsquatting, hallucinated APIs, sycophancy), incident response, GDPR/DACH compliance. MIT, battle-tested.
MIT2026年9月16日 · 指标 2.10.0
Go · npm · PyPI
TM-threemavithana/agentiam
A Postgres wire-protocol proxy that blocks AI SQL injection at the AST level. Protects databases from LLM agents (LangChain, LlamaIndex) by parsing and rewriting destructive queries on the fly.
Apache-2.02026年9月11日 · 指标 2.10.0
Go · PyPI
vaquarkhan/mcp-bastion-suite
Multi-language MCP-Bastion connectors — shared bastion.yaml, adapters for TypeScript/Java/Go/.NET; security engine from PyPI mcp-bastion-python
MIT2026年9月20日 · 指标 2.10.0
PyPI
vdalal/agentx-security-sdk
Runtime action firewall for AI agents: the keyless Shield. Screens catastrophic tool calls (DROP TABLE, SSRF, secret exfil) in-process, no key. Watches by default; set the posture to enforce to block. MIT.
MIT2026年9月11日 · 指标 2.10.0
PyPI
protectai/llm-guard
The Security Toolkit for LLM Interactions
MIT2026年9月17日 · 指标 2.10.0