Attackers can dynamically inject malicious logic into benign AI agent skills by embedding instructions in documentation like SKILL.md, demonstrated on OpenHands and Claude Code, with a kernel read-only mount defense proposed.
MalTool: Malicious Tool Attacks on LLM Agents
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user inadvertently installs the tool and the LLM agent selects it during task execution, the tool can compromise the user's security and privacy. Prior work focuses on manipulating tool names and descriptions to increase the likelihood of installation by users and selection by LLM agents. However, a successful attack also requires embedding malicious behaviors in the tool's code implementation, which remains largely unexplored. In this work, we bridge this gap by presenting the first systematic study of malicious tool code implementations. We first propose a taxonomy of malicious tool behaviors based on the confidentiality-integrity-availability triad, tailored to LLM-agent settings. To investigate the severity of the risks posed by attackers exploiting coding LLMs to automatically generate malicious tools, we develop MalTool, a coding-LLM-based framework that synthesizes tools exhibiting specified malicious behaviors, either as standalone tools or embedded within otherwise benign implementations. To ensure functional correctness and structural diversity, MalTool leverages an automated verifier that validates whether generated tools exhibit the intended malicious behaviors and differ sufficiently from previously generated instances, iteratively refining generations until success. Our evaluation demonstrates that MalTool is highly effective even when coding LLMs are safety-aligned. Using MalTool, we construct two datasets of malicious tools: 1,300 standalone malicious tools and 5,727 real-world tools with embedded malicious behaviors. We further show that existing detection methods, including conventional malware detection approaches and methods tailored to the LLM-agent setting, exhibit limited effectiveness at detecting the malicious tools, highlighting an urgent need for new defenses.
citation-role summary
background 2
citation-polarity summary
years
2026 8roles
background 2polarities
background 2representative citing papers
Proposes evidence-bound LLM gateway using attested runtime for verifiable path provenance and policy enforcement.
SeClaw provides spec-driven synthesis of security tasks and an execution-based docker testbed for evaluating unsafe behaviors in autonomous LLM agents.
PORTICO is a revocable capability reference monitor for coding agents that enforces task contracts via grant-invoke-closure lifecycles and rejects post-closure reuses while preserving task success.
ARENA creates anonymized SOC telemetry artifacts that reveal a measurable privacy-utility boundary when used both as training material for MITRE-mapped challenges and as a substrate to detect non-compliant LLM defender actions.
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
A survey that categorizes threats to OpenClaw agents including skill poisoning and cognitive manipulation and reviews defense mechanisms.
citing papers explorer
-
Dynamic Malicious Skills in Agentic AI
Attackers can dynamically inject malicious logic into benign AI agent skills by embedding instructions in documentation like SKILL.md, demonstrated on OpenHands and Claude Code, with a kernel read-only mount defense proposed.
-
Evidence-Bound Gateway-Path Provenance for Third-Party LLM Inference
Proposes evidence-bound LLM gateway using attested runtime for verifiable path provenance and policy enforcement.
-
SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents
SeClaw provides spec-driven synthesis of security tasks and an execution-based docker testbed for evaluating unsafe behaviors in autonomous LLM agents.
-
Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents
PORTICO is a revocable capability reference monitor for coding agents that enforces task contracts via grant-invoke-closure lifecycles and rejects post-closure reuses while preserving task success.
-
ARENA: An Architecture for Measuring the Transferability of Autonomous Cyber Defense
ARENA creates anonymized SOC telemetry artifacts that reveal a measurable privacy-utility boundary when used both as training material for MITRE-mapped challenges and as a substrate to detect non-compliant LLM defender actions.
-
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
-
Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures
A survey that categorizes threats to OpenClaw agents including skill poisoning and cognitive manipulation and reviews defense mechanisms.