arXiv AI
ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
2d ago
Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks
The paper proposes universal, tool‑based defenses for large language model agents that use external tools, addressing four types of adversarial attacks: direct and indirect prompt injection, memory poisoning, and backdoor attacks. Two main defenses are introduced: Attacker Tool Filtering, which uses anomaly detection to remove suspicious tools, and Normal Tool Recalling, which restores the agent’s original toolset before planning. The authors also add prompt‑based defenses such as Chain‑of‑Thought prompting and self‑reflection, and demonstrate that these methods dramatically lower attack success rates—often to 0%—across multiple open‑source and proprietary LLMs while maintaining or improving task performance.
arXiv AI
Jul 21
STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
arXiv:2509. 25624v3 Announce Type: replace-cross Abstract: As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns.
arXiv AI
Jun 16
AutoDojo: Adaptive Attacks Expose Superficial Defenses and User-Underspecification Limits in LLM Agents
arXiv:2606. 15057v1 Announce Type: cross Abstract: Indirect prompt injection (IPI) is a major security threat to LLM-powered agents.
arXiv AI
Jul 29
Hybrid Analysis for Secure MCP Tool Use in LLM Agents
arXiv:2607. 25297v1 Announce Type: cross Abstract: The rapid development of large language model (LLM) agents has enabled their broad adoption across diverse real-world tasks.
arXiv AI
Aug 28
When Tool Outputs Become Commands: Separating Action Induction from Runtime Authorization in Tool-Augmented LLM Agents
The paper introduces SARA, a framework that separates action induction from runtime authorization in tool‑augmented LLM agents. By treating these as distinct roles, SARA uses an Action Probe to record action provenance and only authorizes tool calls that align with the user objective and past successful executions. Experiments on AgentDojo and AgentDyn show that SARA reduces action‑to‑side‑effect risk to below 0.63% while preserving task performance.
arXiv AI
Jun 18
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.