Skip to content
arxiv papers 1 min read

A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search

Link: http://arxiv.org/abs/2512.01353v1

PDF Link: http://arxiv.org/pdf/2512.01353v1

Summary: Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.

Existing approaches overwhelmingly operate within the prompt-optimization paradigm: whether through traditional algorithmic search or recent agent-based workflows, the resulting prompts typically retain malicious semantic signals that modern guardrails are primed to detect.

In contrast, we identify a deeper, largely overlooked vulnerability stemming from the highly interconnected nature of an LLM's internal knowledge.

This structure allows harmful objectives to be realized by weaving together sequences of benign sub-queries, each of which individually evades detection.

To exploit this loophole, we introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.

The CKA-Agent issues locally innocuous queries, uses model responses to guide exploration across multiple paths, and ultimately assembles the aggregated information to achieve the original harmful objective.

Evaluated across state-of-the-art commercial LLMs (Gemini2.

5-Flash/Pro, GPT-oss-120B, Claude-Haiku-4.

5), CKA-Agent consistently achieves over 95% success rates even against strong guardrails, underscoring the severity of this vulnerability and the urgent need for defenses against such knowledge-decomposition attacks.

Our codes are available at https://github.

com/Graph-COM/CKA-Agent.

Published on arXiv on: 2025-12-01T07:05:23Z