CapLite: Prompt-Injection Defense for Small Language Model Agents without Model-Written Security Artifacts
The paper examines whether small language model agents can be trusted to write the security artifacts used by enforcement-based prompt-injection defenses. Across 15 open-weight models, it reports that model-written policies, graphs and constraints still admit attacks against many models, while CaMeL's programs fail to run in up to 68% of episodes. CapLite instead derives its policy from tool schemas, commits write calls before reading tool results, and only admits writes whose affected recipients, amounts, objects or destinations are stated in the user's request. It reports no successful attacks across 13,935 attacked AgentDojo episodes, with utility under attack of 29.0% versus CaMeL's 27.2% and 17.1k tokens per episode, 18% of CaMeL's token use.
It offers a concrete defense design and evaluation for securing small-model agents against prompt injection without relying on model-generated security policies.
Comments & Questions (0)
No comments yet
Be the first to comment!