Lucene search
+L

677 matches found

Packet Storm News
Packet Storm News
added 2026/04/18 12:00 a.m.15 views

HarmChip: Evaluating Hardware Security Centric LLM Safety Via Jailbreak Benchmarking

The integration of large language models LLMs into electronic design automation EDA workflows has introduced powerful capabilities for RTL generation, verification, and design optimization, but also raises critical security concerns. Malicious LLM outputs in this domain pose hardware-level threat...

5.8AI score
SaveExploits0
Schneier on Security
Schneier on Security
added 2026/04/16 9:41 a.m.16 views

Human Trust of AI Agents

Interesting research: "Humans expect rationality and cooperation from LLM opponents in strategic games." Abstract: As Large Language Models LLMs integrate into our social and economic interactions, we need to deepen our understanding of how humans respond to LLMs opponents in strategic settings. ...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/13 12:00 a.m.20 views

SIR-Bench: Evaluating Investigation Depth in Security Incident Response Agents

We present SIR-Bench, a benchmark of 794 test cases for evaluating autonomous security incident response agents that distinguishes genuine forensic investigation from alert parroting. Derived from 129 anonymized incident patterns with expert-validated ground truth, SIR-Bench measures not only...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/10 12:00 a.m.15 views

RRC Steganography

This is a proof of concept tool called Rotation Range-Coding RRC Steganography - an efficient and provably secure linguistic steganographic method that embeds secret messages into natural-language text generated by large language models. Included is the whitepaper discussing this tool called...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/10 12:00 a.m.11 views

ADAM: A Systematic Data Extraction Attack on Agent Memory Via Adaptive Querying

Large Language Model LLM agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or retrieval-augmented generation RAG mechanisms, enabling them to...

5.8AI score
SaveExploits0
attackerkb
attackerkb
added 2026/04/09 7:45 p.m.7 views

CVE-2026-40088

PraisonAI is a multi-agent teams system. Prior to 4.5.121, the executecommand function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell...

9.6CVSS6.2AI score0.00419EPSS
SaveExploits1References3Affected Software1
Packet Storm News
Packet Storm News
added 2026/04/09 12:00 a.m.12 views

Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain

Large language model LLM agents increasingly rely on third-party API routers to dispatch tool-calling requests across multiple upstream providers. These routers operate as application-layer proxies with full plaintext access to every in-flight JSON payload, yet no provider enforces cryptographic...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/09 12:00 a.m.16 views

Follow My Eyes: Backdoor Attacks on VLM-Based Scanpath Prediction

Scanpath prediction models forecast the sequence and timing of human fixations during visual search, driving foveated rendering and attention-based interaction in mobile systems where their integrity is a first-class security concern. We present the first study of backdoor attacks against VLM-bas...

5.8AI score
SaveExploits0
GithubExploit
GithubExploit
added 2026/04/08 1:53 a.m.171 views

LLMtary

LLMtary Elementary — AI-Powered Penetration Testing Platform...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/08 12:00 a.m.49 views

VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database

Software vulnerabilities continue to pose significant threats to modern information systems, requiring a timely and accurate risk assessment. Public repositories, such as the National Vulnerability Database and CVE details, are regularly updated, but predominantly utilize relational data models...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/08 12:00 a.m.15 views

SentinelSphere: Integrating AI-Powered Real-Time Threat Detection with Cybersecurity Awareness Training

The field of cybersecurity is confronted with two interrelated challenges: a worldwide deficit of qualified practitioners and ongoing human-factor weaknesses that account for the bulk of security incidents. To tackle these issues, we present SentinelSphere, a platform driven by artificial...

5.9AI score
SaveExploits0
OSV
OSV
added 2026/04/07 1:06 p.m.14 views

CVE-2026-5627 Path Traversal in mintplex-labs/anything-llm

A path traversal vulnerability exists in mintplex-labs/anything-llm versions up to and including 1.9.1, within the AgentFlows component. The vulnerability arises from improper handling of user input in the loadFlow and deleteFlow methods in server/utils/agentFlows/index.js. Specifically, the...

9.1CVSS7.2AI score
SaveExploits0References4
GithubExploit
GithubExploit
added 2026/04/07 9:15 a.m.152 views

Benchmarking-Agent-Architectures

Benchmarking Agent Architectures for LLM-Based Exploit Gener...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/07 12:00 a.m.13 views

MA-IDS: Multi-Agent RAG Framework for IoT Network Intrusion Detection with an Experience Library

Network Intrusion Detection Systems NIDS face important limitations. Signature-based methods are effective for known attack patterns, but they struggle to detect zero-day attacks and often miss modified variants of previously known attacks, while many machine learning approaches offer limited...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/07 12:00 a.m.14 views

Your LLM Agent Can Leak Your Data: Data Exfiltration Via Backdoored Tool Use

Tool-use large language model LLM agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats, the risk of systematic data exfiltration by backdoored...

5.9AI score
SaveExploits0
PyPA
PyPA
added 2026/04/06 4:16 p.m.30 views

PYSEC-2026-144

vLLM is an inference and serving engine for large language models LLMs. From 0.7.0 to before 0.19.0, the VideoMediaIO.loadbase64 method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The numframes...

6.5CVSS5.9AI score0.00464EPSS
SaveExploits0References1Affected Software1
CVE
CVE
added 2026/04/06 3:38 p.m.74 views

CVE-2026-34755

vLLM's VideoMediaIO.load_base64("video/jpeg") path has an unbounded frame-splitting bug: data.split(",") bypasses the intended frame-count limit (default 32) used by the binary path, allowing a single request with thousands of comma-separated base64 JPEG frames. This can cause the server to decod...

6.5CVSS6AI score0.00464EPSS
SaveExploits0References12Affected Software1
GithubExploit
GithubExploit
added 2026/04/06 1:02 a.m.151 views

SmartContract-VulnHunter

🛡️ SmartContract VulnHunter The ultimate smart contract securi...

5.9AI score
SaveExploits0
CNNVD
CNNVD
added 2026/04/06 12:00 a.m.17 views

vLLM 安全漏洞

vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Versions of vLLM prior to 0.1.0 to 0.19.0 contained security vulnerabilities. These vulnerabilities stemmed from the lack of upper limit validation for the n parameter in the...

6.5CVSS5.8AI score0.00421EPSS
SaveExploits0References4
GithubExploit
GithubExploit
added 2026/04/05 7:57 a.m.161 views

whitehathackerai

🛡️ WhiteHatHacker AI Autonomous Bug Bounty Hunter — Power...

6.1AI score
SaveExploits0
Rows per page
Query Builder