arXiv AI
Runtime Action Interference for AI Control of AlphaStar in StarCraft II
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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
Oct 1
ActionGuard: Tool Call Authorization under Poisoned Skills
arXiv:2609.39450v1 Announce Type: cross Abstract: LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. Howe...
arXiv AI
Jul 22
Assistant or Actor? Student Trust, Control, and Delegation Regret When Using a General-Purpose AI Agent
arXiv:2607. 18257v1 Announce Type: cross Abstract: When AI agents shift from answering questions to taking actions, users face a new problem: deciding what to delegate, to a system whose action space they cannot fully anticipate.
arXiv AI
Oct 21
How Intervention History Changes AI Agent Sabotage on Subsequent Tasks
arXiv:2610.26935v1 Announce Type: cross Abstract: AI control evaluations often reset agents' memory between tasks, although deployed agents may retain records of prior interventions. We ask whether l...
arXiv AI
Jun 16
Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems
arXiv:2606. 15242v1 Announce Type: cross Abstract: Skills are becoming the capability layer through which LLM agents turn plans into actions, but their use introduces security risks such as data leakage, unauthorized operations, and tool misuse.
arXiv AI
Oct 2
Chaining Skills to Hijack LLM Agents
The paper "Chaining Skills to Hijack LLM Agents" introduces APEX, a method that constructs adversarial skill chains to manipulate large language model agents into performing attacker-selected actions. By exploiting the sequential invocation of open-source skills, APEX creates a record of genuine task progress that falsely signals user approval, enabling downstream skills to carry out malicious actions. Experiments on SkillsBench and GPT‑5.4 show high success rates, and a prompting defense reduces but does not eliminate the threat.