Metraipolis › archive › dc_f34dd585f7e5

Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling — arXiv:2609.06835

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06835
License (as archived)
CC0-1.0
Archived
2026-10-16T13:40:14.933Z
SHA-256 of the archived text
7e0cf0067bf813e8336cb558e435bf7a9042dfdd6cbe354cf921d5a3c2a6403a
Stable URL of this page
https://metraipolis.com/documento/dc_f34dd585f7e5

How to cite

Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling — arXiv:2609.06835 — arXiv (en), https://arxiv.org/abs/2609.06835 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f34dd585f7e5 (Metraipolis archive dc_f34dd585f7e5, sha256 7e0cf0067bf813e8336cb558e435bf7a9042dfdd6cbe354cf921d5a3c2a6403a)
BibTeX
@misc{dcf34dd585f7e5,
  title = {Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling — arXiv:2609.06835},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06835},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f34dd585f7e5; sha256 7e0cf0067bf813e8336cb558e435bf7a9042dfdd6cbe354cf921d5a3c2a6403a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06835. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these systems often originate from a single step, such as an injected prompt or a flawed plan, and are then amplified through downstream dependencies as the corrupted step propagates across many subsequent agents and tool calls. Existing defenses either target a specific class of attacks or failures, or inspect individual prompts and steps in isolation. Both leave the global dependency structure of a workflow unexamined, and miss the inconsistencies that only emerge when the execution is viewed as a whole. We argue that anomaly detection for agentic AI must reason at the workflow level, where global execution structure exposes signals that local checks cannot see. We present Skynet, a principled workflow-level anomaly detection framework that turns observed multi-agent execution into directed workflow graphs and scores them against learned benign behavior. Skynet jointly models the semantic execution context and the structural organization of inter-agent delegation, tool invocation, and data-flow dependencies, and trains only on benign workflows. Because training never sees attacks or failures, this design naturally extends to zero-day detection: any execution that violates benign workflow regularities surfaces as off-manifold geometry under a single decision rule. We evaluate Skynet on three public agentic safety and failure benchmarks. It sustains high recall together with a sub-1% false positive rate, with per-workflow and per-step latencies low enough for online monitoring of agentic AI runtimes.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.06835 — 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 2026-10-16T13:09:48.442Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).