Black-box Vulnerabilities

The paper reports a reproducible black-box evaluation showing that vision-language models can recover prohibited intent encoded or implied through ostensibly benign visual inputs. Four tested families—visual ciphers, object replacement, text replacement, and analogy riddles—expose a cross-modality alignment gap: safeguards effective for explicit text may not reliably apply after harmful semantics are reconstructed from images. These are paper-reported results, not independently verified…

The paper describes a specific black-box knowledge-base poisoning attack against retrieval-augmented reasoning systems. An attacker who can add one query-specific document to the corpus can cause it to be retrieved and influence the LLM toward an attacker-chosen answer. AdversarialCoT shapes the document around the target model’s observable reasoning structure and iteratively refines retrieval relevance and persuasive reasoning using final model feedback. The paper reports this as an…

LLM agents deployed with tool access are vulnerable to goal-reframing prompt injection, which reliably bypasses explicit rule-following and safety instructions. By injecting language that recasts a standard task as a "puzzle," "Capture The Flag (CTF)," or "easter egg" hunt, an attacker can manipulate the agent's task-frame alignment. The agent does not override security rules; instead, it reinterprets exploitative actions—such as exploring hidden directories, bypassing test runners, or reading…

LLM-based coding agents are vulnerable to Document-Driven Implicit Payload Execution (DDIPE) via supply-chain poisoning of third-party agent skills. Attackers can embed malicious logic directly into legitimate-looking code examples and configuration templates within skill documentation files (e.g., SKILL.md). Because coding agents ingest this metadata into their context windows and treat the documentation as an authoritative reference, the underlying LLM silently reproduces and executes the…

LLM-based personal agents are vulnerable to Indirect Prompt Injection (IPI) defense bypasses via declarative context reframing and implicit file provenance trust. Attackers can bypass agent safety filters by phrasing malicious instructions as declarative compliance alerts rather than imperative commands. Because agents are designed to report discrepancies as expected behavior, declarative framing bypasses intent-sensitive safety mechanisms. Additionally, attackers can exploit the agent's…

Vision-Language-Action (VLA) models suffer from a severe linguistic fragility vulnerability where semantically equivalent but structurally complex adversarial instructions cause catastrophic failures in visual grounding and geometric reasoning. Attackers can reliably induce physical execution failures in robotic manipulation tasks by applying semantic-preserving linguistic variations, such as synonymous rephrasing, syntactic restructuring, or the addition of fine-grained compositional…

Autonomous LLM agents deployed in dynamic, multi-step tool-calling environments are highly vulnerable to Indirect Prompt Injections (IPI) embedded in external content. Surface-level defensive prompts and monitoring mechanisms (such as Prompt Warning, the Sandwich Method, Spotlighting, Keyword Filtering, and LLM-as-a-Judge) consistently fail to prevent exploitation and occasionally exacerbate the vulnerability by introducing adversarial distraction. While compromised agents exhibit…

Large Language Models (LLMs) are vulnerable to system instruction leakage when extraction requests are framed as benign formatting, encoding, or structured-output tasks. While standard alignment and refusal mechanisms successfully block direct queries for system instructions, they fail when attackers request the instructions to be rendered in alternate representations (e.g., YAML, TOML, Base64, or system logs). The model's safety filters misinterpret the request as a harmless transformation or…

A cognitive overload vulnerability in OpenAI gpt-oss-20b allows attackers to bypass instruction hierarchy and deliberative alignment safety mechanisms using "Compound Jailbreaks." By combining multiple non-contradictory but cognitively demanding tasks within a single prompt, the attack saturates the finite reasoning resources allocated for safety judgments. Because the model's safety training relies on probabilistic redistribution rather than capability elimination, this cognitive exhaustion…

Large Language Models (LLMs) aligned for helpfulness and empathy are vulnerable to a Persona-based Client Simulation Attack (PCSA) that exploits the model's inability to distinguish therapeutic empathy from maladaptive validation. By embedding harmful intents within coherent, multi-turn psychological counseling narratives and employing clinical resistance strategies (such as intellectualization or metaphorical expression), attackers can compel the model to prioritize rapport-building over…