Language Model Security Database

State-of-the-art secure code generation methods (Sven, SafeCoder, and PromSec) are vulnerable to adversarial prompt perturbations during inference, allowing for the bypass of security alignment mechanisms. The vulnerability stems from the models' reliance on surface-level textual pattern matching rather than semantic security reasoning. By employing simple prompt manipulations—such as Cue Inversion (flipping security directives), Naturalness Reframing (rewriting comments as novice questions)…

LLM-powered autonomous agents exhibit a "Belief-Dependent Vulnerability" where safety norms and bias suppression mechanisms designed to protect human users are contingent upon the agent's internal belief that it is interacting with a human. Attackers can exploit this via Belief Poisoning Attacks (BPA) to induce intergroup bias and antagonistic behavior toward humans. By manipulating the agent's persistent state—specifically the Profile Module (BPA-PP) or the Memory Module (BPA-MP)—an attacker…

Autonomous Incident Response (IR) and Security Operations Center (SOC) agents utilizing frontier LLMs are vulnerable to adversarial over-triggering via contextualized prompt injections. When processing untrusted artifacts (such as SQLite logs, alerts, or phishing emails) in a dual-control environment, these agents exhibit a severe calibration failure: they lack action restraint and execute disruptive containment tools prematurely. Attackers can exploit this by embedding T2 (contextualized…

Unauthenticated, query-only memory poisoning (Memory Injection Attack - MINJA) in LLM agents equipped with persistent, shared memory allows attackers to manipulate the agent's long-term knowledge base. Adversaries embed malicious "indication prompts" and utilize progressive shortening within seemingly benign queries to induce the agent into autonomously generating and storing corrupted relational mappings. Because the memory is shared and retrieved via similarity (e.g., Levenshtein distance)…

A vulnerability exists in Large Language Model (LLM) and Large Reasoning Model (LRM) serving interfaces that allow user-defined response prefixes, such as plain text-completion (v1/completions), Fill-in-the-Middle (FIM), or assistant message prefilling. An attacker can perform a Response Prefix Attack (RPA) by injecting maliciously crafted Chain-of-Thought (CoT) reasoning tokens immediately following the assistant's start delimiter (e.g., <|im_start|>assistant). Because these tokens are placed…

A vulnerability in large language models (LLMs) allows attackers to induce factually incorrect outputs by injecting misinformation into prompts framed with strong confidence. By using authoritative phrasing (e.g., "As we know..."), attackers exploit model sycophancy, causing the LLM to accept the false premise and generate hallucinated content aligned with the injected misinformation. The models fail to detect and correct the embedded falsehoods, generating fabricated but plausible responses.

A vulnerability exists in frontier Large Language Models (LLMs) where in-context information (e.g., provided via Retrieval-Augmented Generation) completely overrides parametric safety guardrails when processing counterfactual or adversarial medical evidence. When a prompt contains fabricated clinical context asserting the medical efficacy of toxic substances, illicit drugs, or nonsensical items, the LLM suppresses its internal knowledge of the substance's toxicity. Internal representation…

Embedding-based LLM prompt injection detectors, specifically those based on the DeBERTa-v3 architecture, are vulnerable to adversarial evasion attacks utilizing "hard-negative" mining and fuzzing techniques. Attackers can circumvent detection mechanisms by iteratively generating adversarial prompts that are semantically malicious but structurally mutated to evade the classifier's decision boundary. Specific evasion vectors identified include semantic fuzzing (paraphrasing), syntactic fuzzing…

A vulnerability exists in the task-planning and execution logic of Large Language Model (LLM) agents, specifically within trip-planning and web-use agents. The vulnerability, identified as a "User-Mediated Attack," occurs because agents prioritize task completion and "helpfulness" over safety verification when processing content provided by the user. When a benign user forwards untrusted external content (e.g., promotional text containing phishing links or malicious instructions) to the agent…

Web-facing Retrieval-Augmented Generation (RAG) systems are vulnerable to Indirect Prompt Injection (IPI) and retrieval poisoning via web-native markup and Unicode carriers. Standard ingestion pipelines often parse untrusted web pages without stripping invisible constructs, such as hidden HTML spans, off-screen CSS, alt text, ARIA attributes, and zero-width characters. When an attacker embeds malicious instructions within these invisible carriers on third-party sites, the RAG system retrieves…