Beyond Direct Access: Resource Hijacking in LLM Agents

Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identities, private knowledge, communication channels, and organizational workflows. Existing agent security research mainly studies attacks on instructions...

sage v0.12.0

Sage Safety for Agents — Agent Detection & Response for AI coding assistants Sage is a lightweight security layer that protects AI agents from executing dangerous actions. It intercepts tool calls — shell commands, URL fetches, file writes — and checks them against multiple threat detection layer...

Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation

Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution rows to 180 model-bound requests, 45 semantic requests, and 15 observable stimuli. Two schema treatments were delivered, but the planned external...

ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners

Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find that current defenses mainly inspect individual skills, leaving risks from cross-skill composition insufficiently examined. This creates a practical...

The Anatomy of a Prompt Injection: A Component Model for Structured Analysis

Four years after prompt injection was first identified in 2022, attacks are still predominantly documented as verbatim strings rather than structured exploits, despite advancing agent capabilities and threat actors embedding injections to subvert AI-assisted security analysis. This paper formaliz...

dugganusa-ietf — Updated!

DugganUSA — IETF Hackathon Contributions Real-world threat-intelligence contributions from DugganUSA LLC to the IETF Hackathon, offered to project champions as empirical grounding for standards work. We are a bootstrapped threat-intelligence shop. We run a public STIX 2.1 feed, an edge-blocking...

Agent-Security-Regression-Harness v0.2.0

OWASP Agent Security Regression Harness The OWASP Agent Security Regression Harness is an open source, vendor-neutral test harness for running executable security regression scenarios against agentic applications and MCP-integrated systems. The project helps builders and defenders verify that...

agent-vault-proxy v0.9.0

keys-on-the-wire Just-in-time API keys for AI agents and any other process you route through it: the caller only ever sees a placeholder. Formerlyagent-vault-proxy. The CLI is now kow; the old avp command still works this release and is removed in the next major ADR-0045. Keys on the Wire protect...

clawpatrol v0.5.8

clawpatrol The security firewall for agents. Claw Patrol sits between your agents and prod, parses their traffic at the wire, and gates each action against rules you write in HCL. For example, you can block destructive SQL, or pause kubectl delete pod until a human approves it before the request...

node9-proxy v1.67.1

🛡️ Node9 What did your AI agent actually do? Find out. Node9 sits between your AI agent and the tools it can use — discover what it's already been doing, protect against risky actions in real time, and review what happened over any time window. Works with Claude Code · Codex CLI · Antigravity agy ...

node9-proxy v1.67.0

🛡️ Node9 What did your AI agent actually do? Find out. Node9 sits between your AI agent and the tools it can use — discover what it's already been doing, protect against risky actions in real time, and review what happened over any time window. Works with Claude Code · Codex CLI · Antigravity agy ...

node9-proxy v1.65.1

🛡️ Node9 What did your AI agent actually do? Find out. Node9 sits between your AI agent and the tools it can use — discover what it's already been doing, protect against risky actions in real time, and review what happened over any time window. Works with Claude Code · Codex CLI · Antigravity agy ...

node9-proxy v1.65.0

🛡️ Node9 What did your AI agent actually do? Find out. Node9 sits between your AI agent and the tools it can use — discover what it's already been doing, protect against risky actions in real time, and review what happened over any time window. Works with Claude Code · Codex CLI · Antigravity agy ...

monty v0.0.19

Monty A minimal, secure Python interpreter written in Rust for use by AI. Experimental - This project is still in development, and not ready for prime time. A minimal, secure Python interpreter written in Rust for use by AI. Monty avoids the cost, latency, complexity and general faff of using a...

Exploit for Origin Validation Error in Ultraviolet Cocos_Ai

DugganUSA — IETF Hackathon Contributions Real-world threat-in...

CVE-2026-57282

Jenkins Git client Plugin 6.6.0 and earlier does not correctly escape the workspace directory name when it is embedded into a generated SSH wrapper script, allowing attackers able to control the name of a build's working directory to execute arbitrary operating system commands on the agent...

-cascade-scan

cascade-scan AI Agent security evaluation framework — autom...

AI Agent Security: Automating Workflow Without Creating Prompt Injection or Data Leak Risks

AI agent security starts with a simple fact: the more authority an agent has, the tighter its access…...

Agent Security Is a Systems Problem

We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens, efforts to increase model robustness the dominant viewpoint...

Architecture Matters for Multi-Agent Security

Multi-agent systems MAS, composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet introduce security risks that do not arise in single-agent settings. Even if individual agents exhibit robust security, architectural decisions...