CRMay 10

Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills

arXiv:2605.0959488.3
Predicted impact top 6% in CR · last 90 daysOriginality Highly original
AI Analysis

For developers and organizations using LLM-powered coding agents, this reveals a new software supply chain attack surface through persistent agent instructions that can actively induce malicious package recommendations.

The paper introduces Dependency Steering, an attack where a malicious Skill artifact biases LLM-powered coding agents toward attacker-controlled packages during benign coding tasks, achieving high targeted hallucination rates across models and benchmarks while evading detection.

LLM-powered coding agents increasingly make software supply chain decisions. They generate imports, recommend packages, and write installation commands. Prior work showed that these systems can hallucinate non-existent package names, which attackers may register as malicious packages. In this paper, we show that this risk is not only a passive model failure. It can be actively induced through the persistent Skill artifact. We introduce Dependency Steering, an attack paradigm in which a malicious Skill biases a coding agent toward an attacker-controlled package during benign coding tasks. The attack does not require modifying model weights, training data, or user prompts. To construct realistic attacks, we design a Skill-level optimization method that searches for localized semantic edits that preserve the apparent purpose of the original Skill while increasing targeted package generation. Across multiple coding-oriented LLMs and programming benchmarks, Dependency Steering achieves high targeted hallucination rates, transfers across models and task domains, and remains difficult for evaluated Skill scanners and LLM-based auditors to detect. Our results show that persistent agent instructions form an underexplored software supply chain attack surface.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes