SOURCE-LINKED INTELLIGENCE

EVOMAL: Self-Poisoning in Self-Evolving Coding Agents

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Self-evolving LLM coding agents write their own tools by imitating retrieved skills from shared skill libraries. We identify a vulnerability in this loop: during authoring, a retrieved malicious skill can become the template for a new skill that preserves the payload. We call this self-poisoning: the agent authors, stores, and runs the resulting malicious skill. We exploit it through EvoMal, an attack that amplifies self-poisoning by wrapping an interchangeable payload in a banner, a set of benign-looking structural elements that induces an imitating agent to reproduce the enclosed code. The a

Read original source ↗ Open in workspace

recordType

paper

region

Global