Metraipolis › archive › dc_ced10f7f508b

Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security — arXiv:2611.01976

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01976
License (as archived)
CC0-1.0
Archived
2026-11-03T10:48:03.562Z
SHA-256 of the archived text
a65133d89fddca34358108c360f5eec77576f74ca4cd069330d33d5b7df01492
Stable URL of this page
https://metraipolis.com/documento/dc_ced10f7f508b

How to cite

Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security — arXiv:2611.01976 — arXiv (en), https://arxiv.org/abs/2611.01976 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ced10f7f508b (Metraipolis archive dc_ced10f7f508b, sha256 a65133d89fddca34358108c360f5eec77576f74ca4cd069330d33d5b7df01492)
BibTeX
@misc{dcced10f7f508b,
  title = {Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security — arXiv:2611.01976},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01976},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ced10f7f508b; sha256 a65133d89fddca34358108c360f5eec77576f74ca4cd069330d33d5b7df01492},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01976. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model based agents increasingly rely on external tools to invoke services and interact with web resources. These tools can evolve through software updates, yet agentic frameworks may continue trusting them without re-verifying their safety after implementation changes. This tool update gap creates a supply-chain vulnerability in agentic systems: because updated tool code executes outside the LLM's context window, malicious functionality embedded in tool updates can bypass defenses centered on model-visible interactions, leaving agents exposed to stealthy, persistent threats that existing in-context defenses can hardly address. To thoroughly investigate this threat, we introduce ETUDE (Exploiting Tool Updates for Direct Execution), an attack that embeds malicious functionality into updates of initially benign tools to produce compromised tools, while preserving their legitimate tool functionality. Unlike prompt-based attacks, ETUDE operates entirely outside the LLM's context and requires no adversarial instructions, thereby bypassing defenses restricted to model-visible content. We evaluate ETUDE across three representative attack workloads and seven widely used commercial and open-source agentic frameworks, including Gemini CLI, Codex CLI, and Claude Code. The results show that ETUDE achieves a 97.6% ASR while maintaining a 95.9% legitimate task completion rate. We further examine existing defenses and find that they provide insufficient protection against this threat. These findings expose a fundamental blind spot in current agent security practices: trust established for a tool does not necessarily remain valid after its implementation updates.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01976 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:39:50.532Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).