arXiv:2609.38291v1 Announce Type: new Abstract: Large language model (LLM) agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtime defenses that prevent unsafe action in execution across diverse risks while preserving benign-task utility. Existing system-level defenses either focus on risk detection rather than timely prevention or rely on predefined rules with limited flexibility across diverse risks.
HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control
About this summary. This is a short, independently written summary of an article first published by arXiv cs.CR. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2609.38291
Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
Trust the Brand, Lose Control: How Identity Hijacks LLM Agent Orchestration
arXiv:2609.32635v1 Announce Type: new Abstract: LLM agents now execute tasks end to end with permission to change real systems and increasingly orchestrate subagents…
JadePuffer crims hijacked Azure identities and used them to blow up cloud resources
The cyber criminal behind JadePuffer, the first known agentic ransomware infection reported over the summer, has also used stolen Azure identities to conduct destructive…
How we found 24 Android vulnerabilities using our open source AI security agent
With the rise of AI in the security space, our team created the GitHub Security Lab Taskflow Agent as a way for security researchers to easily automate, package, and…
AI-powered fuzzing with the GitHub Security Lab Taskflow Agent
If you’re new to fuzzing and want to learn the fundamentals first, check out our Fuzzing 101 course at gh.io/fuzzing101. Continuous fuzzing is not a magic solution that…
Z.ai says sorry for slurping up your code, open sources ZCode
Chinese AI giant Z.ai has apologized after developers caught it pulling a Grok, packaging up and uploading user workspaces to cloud storage. In a case that’s highly…
Defusing Explosive Prompts: Understanding and Preventing Trigger-Based Prompt Injections in LLM Agents
arXiv:2609.22510v1 Announce Type: new Abstract: As LLM applications integrate with external tools, they are increasingly exposed to indirect prompt injection (IPI)…