About Awesome Agent Skills Security
Awesome Agent Skills Security is an MCP server in the Security category: 🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for securing AI agent tool use and skill ecosystems.
Install
From source
git clone https://github.com/LLMSecurity/awesome-agent-skills-securityThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (33)
**[Agent Audit](https://arxiv.org/abs/2603.22853)**Security analysis system for LLM agent apps: dataflow analysis, credential detection, MCP config parsing, privilege-risk checks
Parameters not published.
**[Agent Memory Guard](https://github.com/OWASP/www-project-agent-memory-guard)**OWASP reference implementation for ASI06 (Memory Poisoning): runtime defense that screens every agent memory read/write through detectors + a declarative policy, with source-class provenance, forensic SecurityEvents, and snapshot rollback. LangChain/OpenAI-Agents/AutoGen/CrewAI/mem0 integrations
Parameters not published.
**[Agent Scan](https://github.com/snyk/agent-scan)**Snyk's scanner for local agent supply chains, covering MCP servers and skills with checks for prompt injection, tool poisoning, toxic flows, and malware-laced skill files
Parameters not published.
**[AgentSkillsScanner](https://github.com/sumleo/AgentSkillsScanner)**Static analysis scanner for agent skill definitions
Parameters not published.
**[Armorer Guard](https://github.com/ArmorerLabs/Armorer-Guard)**Local Rust scanner for AI-agent prompt injection, credential redaction, sensitive-data requests, exfiltration-style text, and dangerous tool-call context
Parameters not published.
**[Assay Harness](https://github.com/Rul1an/Assay-Harness)**CI gate that checks an agent's claimed tool side-effects (filesystem, network, process) against independently observed runtime evidence, classifying each claim as supported, degraded, blocked, or not-evaluable (observed support is the ceiling)
Parameters not published.
**[Bounty Sieve](https://github.com/junbuilds96/bounty-sieve)**Offline-by-default bounty intake guardrail for coding agents: read-only GitHub issue/URL-list import, deterministic triage, local decision briefs, and human approval gates
Parameters not published.
**[Clawvisor](https://github.com/clawvisor/clawvisor)**AI agent gateway for purpose-based authorization, credential vaulting, and audit logging — agents declare task scope, humans approve once, Clawvisor enforces on every request without the agent ever seeing credentials
Parameters not published.
**[CubeSandbox](https://github.com/TencentCloud/CubeSandbox)**Hardware-isolated (per-kernel) sub-60ms sandbox for secure AI agent code execution, with an out-of-sandbox credential vault, eBPF network isolation, and domain-allowlisted egress controls with audit logging
Parameters not published.
**[DScan](https://github.com/DeepScan-Security/dscan)**Open-source agent security suite for runtime tool-call tracing, prompt-injection shielding, MCP audits, adversarial testing, and sequence-level attack detection
Parameters not published.
Show all 33 tools
**[Garak](https://github.com/leondz/garak)**LLM vulnerability scanner
Parameters not published.
**[IPI-Proxy](https://github.com/VulcanLab/IPI-Proxy)**Intercepting proxy for red-teaming web-browsing agents against indirect prompt injection on live whitelisted domains
Parameters not published.
**[Invariant Guardrails](https://github.com/invariantlabs-ai/invariant)**Policy-based agent security guardrails
Parameters not published.
**[LLM Guard](https://github.com/protectai/llm-guard)**Input/output scanning for LLM applications
Parameters not published.
**[Lakera Guard](https://www.lakera.ai/)**Enterprise prompt injection defense API
Parameters not published.
**[NeMo Guardrails](https://github.com/NVIDIA/NeMo-Guardrails)**NVIDIA's toolkit for adding guardrails to LLM-based applications
Parameters not published.
**[NemoClaw](https://github.com/NVIDIA/NemoClaw)**NVIDIA reference stack for running always-on AI agents more safely in sandboxes, with network policy, hardening, routed inference, and lifecycle controls
Parameters not published.
**[Nobulex](https://github.com/arian-gogani/nobulex)**Trust Capital scoring layer for AI agents: bilateral Ed25519 receipts (pre- and post-execution signatures), content-addressed via action_ref and hash-chained per RFC 8785, that accumulate into a published 300-850 reputation score gating agent autonomy. CTEF v0.3.2 14/14 conformance. Python + TypeScript SDKs. Receipt-signing approach merged into Microsoft AGT.
Parameters not published.
**[PIC Standard](https://github.com/madeinplutofabio/pic-standard)**Local-first standard and reference verifier that checks agent intent, provenance, and evidence at the action boundary and fails closed before high-impact tool calls; Python CLI, MCP/LangGraph/OpenClaw integrations, HTTP bridge, and a language-agnostic conformance suite
Parameters not published.
**[Pipelock](https://github.com/luckyPipewrench/pipelock)**Open-source AI agent firewall and MCP-aware egress proxy with DLP, prompt injection scanning, process sandboxing, and mediator-signed action receipts
Parameters not published.
**[Promptfoo](https://github.com/promptfoo/promptfoo)**LLM red teaming and evaluation framework
Parameters not published.
**[Rebuff](https://github.com/protectai/rebuff)**Self-hardening prompt injection detector
Parameters not published.
**[Sayfos SDK](https://github.com/sayfos-labs/sayfos-sdk)**Runtime guardrail SDK for AI agents with provenance checks, budget governance, plan preflight, and adjudication tokens before high-risk tool actions
Parameters not published.
**[SkilLock](https://github.com/skills-lock/skil-lock)**Behavior-pinning lockfile + capability-delta PR review for Claude Code & Codex skills; SARIF output for Code Scanning
Parameters not published.
**[SkillGuard](https://github.com/LLMSecurity/skillguard)**LLM-native agent skill security auditor (OWASP Agentic + MITRE ATLAS)
Parameters not published.
**[SkillTotal](https://github.com/pezhik/skilltotal)**Static, offline scanner for AI components (MCP servers, agent skills, npm/PyPI packages, repos): supply-chain risk, dangerous capabilities, prompt-injection, exfiltration; deterministic, evidence-anchored, SARIF + pre-commit/GitHub Action
Parameters not published.
**[Skillid](https://github.com/dkoly/skillid)**Policy-driven Claude Code plugin that combines skill guidance with per-tool hooks to enforce org guardrails, confirmation rules, redaction, and connector-specific access control
Parameters not published.
**[Tuning Engines CLI](https://github.com/cerebrixos-org/tuning-engines-cli)**MCP server and CLI for governed agent/skill/tool access with policy checks, approvals, traces, and role-scoped registries
Parameters not published.
**[agent-diff-guard](https://github.com/cubxxw/agent-diff-guard)**Pre-push guardrail that flags high-risk coding-agent diffs such as CI/CD changes, dependency edits, test deletions, hardcoded secrets, and task-scope drift before merge
Parameters not published.
**[agent-sentinel](https://github.com/junlinwk/agent-sentinel)**eBPF/BPF-LSM prototype that monitors local agent behavior and atomically blocks prompt-injection-driven access to sensitive files at the kernel boundary
Parameters not published.
**[mcp-sec-audit](https://arxiv.org/abs/2603.21641)**MCP server security toolkit: static pattern matching + dynamic sandboxed fuzzing via Docker/eBPF for detecting over-privileged tool capabilities
Parameters not published.
**[mcp-sploit](https://github.com/Prasanna-27eng/mcp-sploit)**Metasploit-style framework for authorized security testing of MCP servers and MCP security gateways, including enumeration and exploit modules for unsafe tool exposure
Parameters not published.
**[trentclaw](https://github.com/trnt-ai/trent-openclaw-security-assessment)**Security assessment skill for OpenClaw environments: scans gateway config, skill permissions, MCP trust boundaries, and plugins, and correlates them into chained attack paths with severity-ranked remediation steps
Parameters not published.
Ask AI
✦
Ask AI about Awesome Agent Skills Security
Powered by Claude · Grounded in docs
I know everything about Awesome Agent Skills Security. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.