Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents

Large language model LLM-based agents increasingly connect model-generated decisions to security-sensitive software capabilities such as command execution, filesystem access, network communication, browser control, and external tools. Existing analyses often use predefined sensitive operations as...

Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context

SummaryDecepticon wraps web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK Bring Your Own Key deployment model, users configure their own LLM credentials to any OpenAI-compatible...

KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards

LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowledge-based assessments or end-to-end agentic tasks, and do not directly measure LLMs' ability to generate executable...

MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication

Inter-agent communication is central to Large Language Model Multi-Agent Systems LLM-MAS, but it introduces an underexplored vulnerability: Agent-in-the-Middle AiTM attacks that manipulate messages in transit without compromising the agents themselves. Prior work reports Attack Success Rates ASR...

Xalgorix Autonomous AI Pentesting Agent 4.6.128

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild

LLM agents increasingly rely on activation probes as runtime monitors for prompt injection, jailbreaks, and unsafe requests, reading the model's own hidden state to catch a harmful input before the agent acts on it. A cheap, increasingly common move, borrowed from LLM-as-judge prompting, is to...

Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations

Large language models LLMs in production systems face prompt injections, trojans backdoors, and manipulation of automatic quality metrics. This thesis develops models, methods, and algorithms for evaluating and improving LLM robustness to adversarial input sequence variations. We propose Rstabf, ...

OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents

LLM agents with tool-calling capabilities can access external services and private user data, but they may retrieve more information than a user's request explicitly requires. We study this behavior in structured tool-calling agents and term it proactive over-authorization. This setting differs...

Chaining Skills to Hijack LLM Agents

LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowing information produced under one skill to guide the next. Because skills may come from open-source repositories, this handoff can also carry...

Autonomous OSS Threat Detection Via Taxonomy-Aligned LLMs

Open source software OSS ecosystems face growing threats from sophisticated supply chain attacks including typosquatting, dependency confusion, Trojan Source obfuscation, malicious build injection, and CI/CD pipeline poisoning. Existing detection approaches rely on signature-based tools and...

CVE-2026-102911

A flaw has been found in zosmaai pi-llm-wiki up to 0.11.7. Affected is an unknown function of the file mcp/index.ts of the component wikicapturesource MCP tool. Executing a manipulation of the argument url can lead to os command injection. The attack can be executed remotely. The exploit has been...

CVE-2026-102911 zosmaai pi-llm-wiki wiki_capture_source MCP tool index.ts os command injection

A flaw has been found in zosmaai pi-llm-wiki up to 0.11.7. Affected is an unknown function of the file mcp/index.ts of the component wikicapturesource MCP tool. Executing a manipulation of the argument url can lead to os command injection. The attack can be executed remotely. The exploit has been...

CVE-2026-102911 zosmaai pi-llm-wiki wiki_capture_source MCP tool index.ts os command injection

A flaw has been found in zosmaai pi-llm-wiki up to 0.11.7. Affected is an unknown function of the file mcp/index.ts of the component wikicapturesource MCP tool. Executing a manipulation of the argument url can lead to os command injection. The attack can be executed remotely. The exploit has been...

CVE-2026-102911

A vulnerability exists in zosmaai pi-llm-wiki versions up to 0.11.7 within the wiki_capture_source MCP tool . Specifically, an unknown function in the mcp/index.ts file fails to properly handle the url argument, leading to os command injection . This flaw can be exploited remotely , and a proof-o...

EUVD-2026-89606

A flaw has been found in zosmaai pi-llm-wiki up to 0.11.7. Affected is an unknown function of the file mcp/index.ts of the component wikicapturesource MCP tool. Executing a manipulation of the argument url can lead to os command injection. The attack can be executed remotely. The exploit has been...

CVE-2026-102911 zosmaai pi-llm-wiki wiki_capture_source MCP tool index.ts os command injection

A flaw has been found in zosmaai pi-llm-wiki up to 0.11.7. Affected is an unknown function of the file mcp/index.ts of the component wikicapturesource MCP tool. Executing a manipulation of the argument url can lead to os command injection. The attack can be executed remotely. The exploit has been...

Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents

LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabilities and, once installed, can be automatically invoked across subsequent user tasks. This creates a chain of trust in which users delegate authori...

No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents

Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement learning RL and large language models LLMs offer complementary mechanisms for the planning and execution such agents require, and prior work has...

PT-2026-103015

A flaw has been found in zosmaai pi-llm-wiki up to 0.11.7. Affected is an unknown function of the file mcp/index.ts of the component wiki capture source MCP tool. Executing a manipulation of the argument url can lead to os command injection. The attack can be executed remotely. The exploit has be...

MADBench: Benchmarking the Security of Multi-Agent Debate

Multi-agent debate MAD can improve large language model LLM reasoning by allowing multiple agents to exchange and critique their answers to the same task. However, the interactions that enable agents to correct mistakes can also spread adversarial errors and steer the agents toward an incorrect...