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
- CHRONO-RESOLUTION: A Dependency Resolution Dataset at Release Points for npm, PyPI, and crates.io Packages20 Jul
- SleeperGem: RubyGems supply chain attack targets dormant maintainer accounts19 Jul
- Seven Malicious Vite npm Packages Use Blockchain C2 to Deliver a RAT17 Jul
- VulnHunter: Capital One's agentic AI code security tool17 Jul
- The Prover Is the Judge: Verified Security Software from AI Coding Agents in Ada/SPARK17 Jul