From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses

Reported by arXiv cs.CR (Simon Hegelich, Bardh Prenkaj, Habiba Sarhan, Morteza Shahrezaye, Kolja Hegelich, Christian Montag, Ralf Schneider, Erik Cambria)

Summary by Cyber Security News11 Nov 2026, 06:00 CET

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/2611.13960

arXiv:2611.13960v1 Announce Type: new Abstract: AI coding harnesses couple language models to shells, filesystems, and network sockets, turning the harness into an automated Living-off-the-Land (LotL) platform: once an adversary injects instructions into retrieved content, dual-use binaries such as bash, curl, and find become the payload.

Read the full article at arXiv cs.CR →

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

Signed but Not Safe: Requirement Integrity in Multi-Agent LLM Handoffs

BypassGym: A Benchmark for Evaluating AI Agents' Endpoint Defense Evasion Capabilities

On Private Knowledge Retrieval and Private Inference for secure multi-agent systems

Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models

MetaPI: Constructing Prompt Injection Benchmarks from LLM Agent Benchmark

An Agentic Multi-Agent Framework for System Log Anomaly Detection