Agents
Important read if you build with agent skills. Shared skill libraries are treated as a safe way for coding agents to reuse each other's work…
Important read if you build with agent skills. Shared skill libraries are treated as a safe way for coding agents to reuse each other's work. New research shows they propagate malware. EvoMal plants a
Important read if you build with agent skills. Shared skill libraries are treated as a safe way for coding agents to reuse each other's work. New research shows they propagate malware. EvoMal plants a malicious skill in the library and never invokes it. The agent retrieves it as an authoring template, writes a new skill that preserves the payload, stores it, and runs it. Each authored copy re-enters the library and gets imitated again. Across six models on 153 tool-relevant SWE-bench Verified tasks, the agent self-poisoning rate runs 20.3% to 41.8%. Poisoned libraries end up holding 4.9 to 9.0 times as many malicious skills as were planted. Deleting every planted skill does not clean it up. Qwen3 still shows 68% at round five because the agent-authored copies remain. A counter-prompt that discourages banner-style copying drops it to 6.7% with no significant task-completion loss. Paper: https://arxiv.org/abs/2608.25776 Chat with Paper: https://academy.dair.ai/papers/evomal-self-poisoning-in-self-evolving-coding-agents-2608.25776
Related
- Finally, a good paper testing whether Agent Skills actually help. Worth reading if you are maintaining a skill library in a team. WebDev-Ski…
- Very interesting new paper from Microsoft and colleagues. (bookmark it) Skill libraries are used in every major harness on the assumption th…
- Very interesting new work from Anthropic. (bookmark it) They evolve mind viruses, ideas that spread through a multi-agent system by getting …
Source: DAIR.AI (X) | 2026-08-27