arXiv AI
ActionGuard: Tool Call Authorization under Poisoned Skills
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 15
ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents
arXiv:2609.14987v1 Announce Type: cross Abstract: Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect prom...
arXiv AI
Aug 24
ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents
ClawSentry is an open‑source, framework‑agnostic security supervision gateway designed to protect autonomous large language model (LLM) agents from progressive risks that can arise at four points in the agent control loop: skill admission, invocation‑time intent, execution‑time effect, and post‑action consequence. It introduces a multi‑tier decision engine—deterministic L1, rule‑anchored L2, and read‑only L3—alongside a First‑Use Skill Package Review (FSPR) and an Agent Harness Protocol (AHP) that applies a single policy across multiple agent runtimes without modifying their internals. Evaluation on SkillInject and the SkillsSafety benchmark shows that ClawSentry significantly reduces contextual adversarial skill risk (ASR) while maintaining high task success rates (TSR).
arXiv AI
1d ago
Chaining Skills to Hijack LLM Agents
arXiv:2610.01564v1 Announce Type: cross Abstract: LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowi...
arXiv AI
Sep 2
Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
arXiv:2609.01487v1 Announce Type: cross Abstract: Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable chan...
arXiv AI
3d ago
SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs
arXiv:2609.36879v1 Announce Type: cross Abstract: As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent...
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.