github.com
Agent Memory Guard
OWASP project providing a runtime defense layer that screens AI agent memory reads and writes against prompt injection, secret leakage, and memory poisoning
Independent evaluation guide | 11 synced entries
How to evaluate AI agent and MCP security tools
Secure agent tools, memory, identity, permissions, sandboxes, and MCP servers. Compare selection criteria here, then verify every claim against the linked first-party source.
Decision context
What does agent security tooling need to cover?
AI agent security focuses on systems that can choose actions, call tools, retain memory, and interact with external services. These capabilities turn prompt injection and untrusted context into authorization and execution risks. Model Context Protocol servers add another integration boundary involving tool descriptions, credentials, transport, and user approval. Tools in this category inspect agent workflows, scan MCP or skill definitions, protect memory, test excessive agency, and isolate runtime actions.
README-synced directory
AI Agent and MCP Security catalog entries
Each listing preserves the neutral description maintained in the Awesome MLSecOps README and links to the resource's first-party source.
github.com
Agent-Wiz
Python CLI by Repello AI for extracting agentic workflows from LangChain/LangGraph/CrewAI/AutoGen and running automated threat modeling
github.com
Agentic Security
Agentic LLM Vulnerability Scanner / AI red teaming kit
github.com
Bifrost
Go-native AI gateway that enforces guardrails, rate limits, and fine-grained access controls across LLM and MCP traffic.
github.com
HOL Guard
Open-source local-first runtime security layer for AI agents that evaluates supported tool actions and local artifacts for prompt injection, secret exposure, unsafe commands, package risks, and MCP threats
github.com
Humanbound
Open-source CLI that sends LLM-generated adversarial attacks to an agent's HTTP endpoint and scores results against OWASP LLM Top 10, OWASP Agentic Top 10, NIST, and EU AI Act mappings
github.com
IronClaw
Self-hosted runtime that sandboxes autonomous AI agents with isolated execution, restricted networking, and human-approval gating
github.com
Prismor
Self-hosted runtime control plane that screens AI coding-agent tool calls against a signed policy before execution, blocking or routing to human approval secret exfiltration, prompt-injection-driven actions, and destructive commands across Claude Code, Codex, and MCP servers
github.com
skill-audit-mcp
Static security scanner for MCP servers, AI agent skills, and plugins, with SARIF output and CI integration
github.com
SourceryKit
Verifies an AI agent's outbound requests and MCP handoffs against a source of truth using zero-knowledge proofs, so a call only goes out if its claims check out; hooks the HTTP libraries, logs each outbound call, and blocks endpoints not on the trusted allow-list
trent.ai
Trent AI
Agentic AI security platform that continuously assesses AI agents, MCP servers, LLM and AI-native applications, and code shipped with AI coding tools, traces attack chains, and verifies proposed fixes landed
No catalog entries match that search.
Selection framework
How should teams evaluate the options?
Assess agent-security tooling against the permissions and data paths in your architecture. Look for explicit identities, least-privilege scopes, per-tool policy, credential isolation, network controls, and durable audit records. Define which actions require human approval, such as financial transactions, data mutation, privilege changes, or external communications, and make unavailable approval or policy services fail closed. A scanner should cover indirect prompt injection and malicious tool metadata, not only user prompts. Test the complete action path because a safe model response can still trigger an unsafe downstream tool call.
- 01Tool-level authorization
- 02Memory and context controls
- 03Sandbox boundaries
- 04Audit and approval workflows
Record evidence and limitations for each criterion. A catalog listing is a discovery aid, not a security certification.
Primary references