arXiv:2610.29869v1 Announce Type: new Abstract: Coding agents that run long enough must compact their context, summarizing the conversation, discarding the original, and carrying the summary forward as memory. We show that in popular open-source coding agents this step is an exploitable trust boundary.
Compaction Laundering: Provenance Destruction in Context-Compacting Coding Agents
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/2610.29869
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
Kerkoporta: Injecting Structured-Output Backdoors in Reasoning Coding Agents
arXiv:2611.00138v1 Announce Type: new Abstract: Existing large language model (LLM) backdoor attacks operate primarily in chat settings, where the risk is bounded by…
Claude Code extension poisoned with persistent SSH backdoor
A tampered build of Anthropic’s Claude Code extension for VS Code-compatible editors planted an SSH backdoor on developers’ machines, researchers at macOS security firm…
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…
SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 4
Security Affairs AI-CYBERSECURITY newsletter includes a collection of the best articles and research on AI in the international landscape Artificial intelligence is…
Vulnerable Models in the AI Supply Chain: An Empirical Study of Adoption, Propagation, and Usage Patterns
arXiv:2610.12893v1 Announce Type: new Abstract: The rapid integration of Artificial Intelligence (AI) models has established a complex supply chain, but many of these…
Hacking on Autopilot: Inside ARTEX Cybercrime Campaigns
Key Points Agentic hacking platforms like ARTEX, where AI models autonomously drive vulnerability discovery and exploitation, have been observed to be used by various…