arXiv AI
Jul 1
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
Pincer: Resource Authorization for Agents using a Digital Twin
Pincer is a defense mechanism for coding agents that operates at the resource layer, complementing existing tool‑call defenses. It uses a digital twin—an isolated‑context model that learns and enforces dynamic, user‑specific least‑privilege policies—to act as a proxy for the agent’s permission requests. The authors introduce a user‑centric dataset to emulate the learning phase and demonstrate that Pincer outperforms several baselines in both security and utility, especially against adversarial attack types.
Related stories
arXiv AI
Jun 2
AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.
arXiv AI
Jul 7
Towards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation
arXiv:2603. 17673v2 Announce Type: replace-cross Abstract: LLM agents are becoming increasingly important in the security domain, but leading systems are often closed-source, cloud-based, hard to reproduce or use with sensitive code.
arXiv AI
Jul 7
When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents
arXiv:2607. 05189v1 Announce Type: cross Abstract: Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proactive background execution.
arXiv AI
Sep 1
SIR: Self-improving Red-teaming for Compute Use Agents
arXiv:2608.30207v1 Announce Type: cross Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal...
arXiv AI
Jun 6
CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
arXiv:2601. 09923v3 Announce Type: replace Abstract: AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior.
arXiv AI
Jul 8
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
arXiv:2603. 02277v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, creating novel security risks.
arXiv AI
Sep 10
AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill Stealing
The paper introduces AgentLeak, a black‑box attack that clones the task‑solving capabilities of a strong LLM agent onto a weaker one by exploiting differences between successful and failed executions. Unlike prior skill‑stealing methods that only recover explicit skill artifacts, AgentLeak identifies and incorporates missing procedural behaviors, boosting task pass rates by over 40% and closing more than 80% of the capability gap across 20 scenarios. The study demonstrates that observable execution behavior can leak proprietary procedural knowledge, posing a confidentiality risk for LLM agents.
arXiv AI
Jun 16
FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion
arXiv:2606. 15609v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on long-term memory to support complex task execution, user personalization, and domain adaptation.
arXiv AI
Jun 2
Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems
arXiv:2606. 00925v1 Announce Type: cross Abstract: Open agent platforms allow community contributors to publish reusable skills that agents can invoke at runtime.
arXiv AI
Sep 1
Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection
arXiv:2608.30041v1 Announce Type: cross Abstract: Large language model agents place outputs from external skills into their execution context, allowing attacker-controlled data to influence later pri...
Hugging Face Trending Papers
Aug 31
SIR: Self-improving Red-teaming for Compute Use Agents
Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal, and they are increasingly deployed to automate ev...