arXiv:2611.10542v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly improve themselves through self-evolution, distilling execution experience into persistent, reusable skills. However, this persistence creates a new attack surface: malicious rules implanted into skills can compromise subsequent agent behavior.
When Experience Becomes a Backdoor: Poisoning Self-Evolving LLM Agents via Failure-Aware Task Optimization
About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2611.10542
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
Agentic Backdoors via Pretraining Poisoning
arXiv:2610.37741v1 Announce Type: new Abstract: Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security risk…
LiteLLM Hijacked Again: Malicious 1.107.0 Wheels Steal Credentials and Load Remote Code
The JFrog Security Research team identified malicious code in `litellm` 1.107.0, a widely used Python interface and proxy for large language model providers. The payload…
Fake GitHub Security Tools Infect Over 2,000 PCs With Malware
Fake GitHub security tools are spreading malware that disables defenses, steals sensitive data and infects over 2,000 PCs. Cybersecurity firm Doctor Web has found…
SECURITY AFFAIRS MALWARE NEWSLETTER ROUND 122
Security Affairs Malware newsletter includes a collection of the best articles and research on malware in the international landscape Malware Newsletter Unknown APT uses…
Fake security tools on GitHub push backdoors and infostealers
Cybersecurity professionals are being targeted with infected security projects on GitHub that deploy a backdoor and information stealer malware.
Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks
arXiv:2611.07640v1 Announce Type: new Abstract: Indirect prompt-injection (IPI) benchmarks predominantly test planted instructions that redirect a tool-using agent…