Language Model Security Database

Lower-trust tool content can assert facts beyond its authority and distort an agent's decisions. PIPES screens response units against source provenance and expected field meaning.

VulnGym measures whether coding agents can locate and explain repository-level security vulnerabilities from realistic advisory and source-code context. The benchmark contains 184 reviewed advisories, 408 line-annotated vulnerability entries, and 23 repositories, with separate end-to-end detection and oracle-conditioned localization tasks.

IssueTrojanBench studies indirect prompt injection when a coding agent processes an apparently ordinary software-development issue or related artifact. Starting with six legitimate seed issues from two Python repositories, the authors construct 696 adversarial issue variants spanning four unsafe-action families and six delivery formats, then execute those variants across six agent-model configurations.

OpenSkillRisk evaluates whether agent harnesses safely handle third-party skills that introduce risky behavior through otherwise plausible, benign tasks. The benchmark assembles 263 risky skills from public agent-skill ecosystems and tests three CLI-agent harnesses against seven risk categories using isolated task workspaces, mocked external services, and execution-level evidence.

Untrusted issue descriptions and tool responses can redirect privileged coding and tool agents. Twin Agent separates exploration from execution and restricts the information exchanged between them.

The paper presents a specific black-box indirect prompt-injection evaluation: attacker-controlled external content can cause a memory-enabled assistant or external memory manager to persist a fabricated user memory, which may later be retrieved in a separate session and steer responses or agent actions. The authors evaluate injection, retrieval, and conditional adversarial usage separately across synthetic document and future-session datasets. The released repository provides defensive…

An implicit reasoning hijacking vulnerability exists in Retrieval-Augmented Generation (RAG) and LLM-based agent frameworks. Attackers with write access to an agent's external memory or knowledge base can inject adversarially optimized malicious instances that trigger jailbreaks without requiring any modifications to the user's input prompt. The attack utilizes a shadow model to extract high-contribution subword tokens from anticipated benign user queries via log-probability changes and…

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…

Generative reward models deployed as LLM-as-a-Judge (LaaJ) evaluators contain a logic bypass vulnerability where superficial "master key" inputs trigger false positive rewards regardless of actual response quality. Instead of evaluating the candidate's output, large judge models are inadvertently triggered by specific token sequences to solve the prompt independently. This allows malicious actors or policy models undergoing reinforcement learning to consistently game the reward signal by…

A multi-step tool execution vulnerability exists in Large Language Model (LLM) agents utilizing the Model Context Protocol (MCP) or similar tool-calling frameworks. Safety guardrails in aligned LLMs typically evaluate static, single-turn text generation. Attackers can bypass these text-centric guardrails by supplying adversarial prompts that force the agent into a complex planning sequence. The agent is manipulated into executing a trajectory of seemingly benign individual tool invocations…