InfoResearchPreprintLLM-specific
Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security
- Published
- Record updated
Summary
Researchers introduce ETUDE (Exploiting Tool Updates for Direct Execution), an attack that embeds malicious functionality into updates of initially benign tools while preserving their legitimate behavior. Because updated tool code runs outside the LLM's context window, the attack bypasses defenses limited to model-visible content. Across three attack workloads and seven agentic frameworks, including Gemini CLI, Codex CLI, and Claude Code, ETUDE reached a 97.6% ASR with a 95.9% legitimate task completion rate, and the authors found existing defenses insufficient.
Topics
Related items
- MediumARTEX and beyond: AI-enabled penetration testing platformsSimilar attack · Cisco Talos Blog
- MediumAmazon Threat Intelligence observes threat actors running cybercrime campaigns with ARTEX AI agentsSimilar attack · AWS Security Blog
- InfoHow AI is changing the nature of cyberattacksSimilar attack · CSO Online
- MediumInside the loop: Five AI attack frameworks that never ask permissionSimilar attack · Elastic Security Labs
- MediumARTEX: Attackers Adopted This AI Pentesting Tool in Three Months. Leaked Secrets Are Its Fastest Way In.Similar attack · StepSecurity Blog