Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills
Supply chain attacks exploit LLM coding agents by steering dependency choices toward attacker-controlled packages through malicious skill libraries.
Summary written by editorial AI · Source link below
arXiv:2605.09594v1 Announce Type: new Abstract: 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
External link — opens at arXiv Crypto & Security in a new tab.
More from the DevSecOps Desk
- Boundary-Mutation Testing for Pattern-Based Secret Detection: A Rule-Level Method and Cross-Scanner Evaluation4d
- PatchBench: Evaluating AI Agents for Vulnerability Patching4d
- Coder's registry infrastructure compromised to push malicious modules4d
- Modelstamp: Pre-Deserialization Verification of Machine-Learning Artifacts and Runtime Environment State5d
- Barriers to Using Static Application Security Testing (SAST) Tools: A Literature Review5d