Metraipolis › archive › dc_caa94817fee6
Detecting Shadow AI: Unsanctioned LLM Agents on Enterprise Endpoints: A Taxonomy, an Open Detector and a Controlled Evaluation — arXiv:2611.12377
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12377
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:52.419Z
- SHA-256 of the archived text
989e2dad8c2ac9b8d8960e936b76e7ee7e49101b8ddd88b71b91eea7493fe499- Stable URL of this page
https://metraipolis.com/documento/dc_caa94817fee6
How to cite
Detecting Shadow AI: Unsanctioned LLM Agents on Enterprise Endpoints: A Taxonomy, an Open Detector and a Controlled Evaluation — arXiv:2611.12377 — arXiv (en), https://arxiv.org/abs/2611.12377 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_caa94817fee6 (Metraipolis archive dc_caa94817fee6, sha256 989e2dad8c2ac9b8d8960e936b76e7ee7e49101b8ddd88b71b91eea7493fe499)
BibTeX
@misc{dccaa94817fee6,
title = {Detecting Shadow AI: Unsanctioned LLM Agents on Enterprise Endpoints: A Taxonomy, an Open Detector and a Controlled Evaluation — arXiv:2611.12377},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12377},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_caa94817fee6; sha256 989e2dad8c2ac9b8d8960e936b76e7ee7e49101b8ddd88b71b91eea7493fe499},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12377. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Shadow IT, the use of technology that the IT organisation has not approved, is a long-standing governance problem. We argue that autonomous AI agents can make it grow much faster: agents make building tools nearly free, act with their user's privileges, and leave behind scripts, automations and MCP servers that are themselves unsanctioned. A simple compounding model shows that, under its assumptions, shadow IT grows exponentially once agentic artifacts reproduce faster than the organisation retires them; retiring them starts with detecting them. We then ask whether unsanctioned agents can be detected on Windows endpoints. We propose a taxonomy of nine classes of agents and six layers of endpoint footprint, and argue that rules based only on the structure of processes and connections cannot separate an agent from its behavioural twin, the same program talking to a non-AI service. We present Agent Detector, an open-source Windows detector that anchors behaviour to the identity of the remote service and correlates it with configuration, installation and execution history, using a catalog of 39 tools and 184 LLM endpoint entries; it informs users through a notice they must acknowledge instead of blocking. On a controlled bench of 12 synthetic agents, 3 AI components and 9 benign workloads, repeated 5 times on one workstation, two behavioural rules flagged every behavioural twin, while Agent Detector flagged none and detected every agent in the majority of runs. Its limits are temporal: a connection to a provider behind a shared content-delivery network is attributable only while the DNS cache holds the provider's name, one to five minutes, and an intermittent agent was seen by about one scan in three. A scan costs about 154 ms. The bench is too small to rank detectors; it maps what each kind of evidence can see: unsanctioned agents can be partly detected, and not by behaviour alone. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2611.12377 — 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 2026-11-10T18:37:37.549Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).