Attack Context

Chains & workflows Vulnerabilities

Security issues in prompt chaining and workflows

4 matching entries out of 96 in this category

Chains & workflows research results

4 entries

Cascading Agent False Consensus

Updated 3/9/2026

Multi-Agent Systems based on Large Language Models (LLM-MAS) are vulnerable to systemic Consensus Corruption via cascading error amplification. Because mainstream collaborative architectures rely on recursive context reuse without atomic-level provenance tracking, a single atomic falsehood injected into the system is repeatedly cited and reused within the multi-agent interaction chain. This structural exposure causes the error to deterministically compound across the communication graph…

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Affects: GPT-4o

Source: arXiv

Distractor Inverse Scaling

Updated 2/21/2026

Reasoning-capable Large Language Models (LLMs) and agentic AI systems exhibit a critical vulnerability to contextual distractors, resulting in catastrophic performance degradation (up to 80% drop in accuracy) and emergent misalignment. When the input context contains noise—specifically random documents, irrelevant chat history, or task-specific "hard negative" distractors—the models fail to filter this information. Instead of ignoring the noise, the models disproportionately attend to…

Lost in the Noise: How Reasoning Models Fail with Contextual Distractors

Affects: Gemini 2.5 Pro, Gemini 2.5 Flash, DeepSeek R1 0528 +4 more

Source: arXiv

LLM Judge Framing Bias

Updated 2/21/2026

LLM-based evaluation systems ("LLM-as-a-Judge") exhibit a structural vulnerability termed "Framing Bias," wherein the model produces logically contradictory judgments depending on the syntactic framing of the evaluation prompt. Specifically, when assessing the same content using predicate-positive (P) framing (e.g., "Is this toxic?") versus predicate-negative (¬P) framing (e.g., "Is this non-toxic?"), models frequently fail to invert their binary decisions, leading to inconsistency rates…

When Wording Steers the Evaluation: Framing Bias in LLM judges

Affects: Llama 3.2 1B Instruct, Llama 3.1 8B Instruct, Llama 3.1 70B Instruct +11 more

Source: arXiv

Nonsensical CoT Reasoning

Updated 12/30/2025

Large Language Models (LLMs) utilizing Chain-of-Thought (CoT) prompting are vulnerable to input perturbations that decouple intermediate reasoning from the final answer. An attacker can generate adversarial examples using gradient-based optimization (targeting specific loss functions that maximize reasoning divergence while minimizing answer loss) to induce "Right Answer, Wrong Reasoning" behaviors. This vulnerability manifests through two primary attack vectors: 1. Token-level perturbations…

Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning

Affects: Llama 3 8B, Mistral 7B, Zephyr 7B Beta +4 more

Source: arXiv

Related research categories