oversight

Oversight v0.5.8 Oversight est un outil de renseignement de sécurité basé sur le terminal, conçu pour auditer les scripts shell et les commandes avant qu'ils n'entrent en contact avec votre système. Il comble le fossé entre la « confiance aveugle » et l'« audit manuel » en fournissant une analyse...

deleting-the-trace

Атаки с внедрением управляющих токенов на агентов, использующих инструменты Код и зарегистрированные измерения для исследования двух атак на уровне входных данных на агентов на основе языковых моделей, использующих инструменты. Первая атака добавляет короткую строку собственных управляющих токено...

LAAF: A Layered Accountability Architecture Framework for LLM Applications

Large Language Models LLMs operate in hospitals, courtrooms, banks, and public service desks, where fluent, confident outputs are treated as authoritative even when ungrounded or incorrect. When such an output contributes to harm, who is answerable, and through what mechanisms can responsibility ...

The County Prosecutors Who Became ICE Informants

Illinois prosecutors shared defendants’ personal data with federal immigration agents without criminal warrants, public disclosure, or legislative oversight...

Beyond the Hype: Evaluating LLM Integration and Practical Limitations in Security Operation Centers

Large Language Models LLMs are increasingly being explored within Security Operation Centers SOCs to support text-heavy analytical work such as alert contextualization, incident summarization, and drafting investigative artifacts. Despite this interest, practitioners describe critical operational...

Trump Memo Paves Way for U.S. Firms to Hack and Disrupt Foreign Crime Groups

A new White House memo signed by U.S. President Donald Trump has instructed the National Coordination Center NCC to establish a program that would allow private sector companies to take advantage of their "innovative capabilities" to break into foreign Transnational Criminal Organizations TCOs an...

CVE-2026-12940 Langflow is affected by remote code execution due to multiple unauthenticated and insufficiently authorized API endpoints

IBM Langflow OSS 1.0.0 through 1.10.1 are vulnerable to unauthenticated remote code execution via environment variable injection in the MCP Model Context Protocol stdio launcher. The vulnerability exists in src/lfx/src/lfx/base/mcp/util.py where the DANGEROUSENVVARS blocklist fails to include...

ICE’s New Detention Center Contracts Declare State Laws ‘Shall Not Apply’

One day after a federal judge ordered an ICE detention center opened to state health inspectors, the agency posted new contract terms that would void state oversight at four facilities...

oversight v0.5.8

Oversight v0.5.8 Oversight is a terminal-based security intelligence tool designed to audit shell scripts and commands before they touch your system. It bridges the gap between "blind trust" and "manual auditing" by providing a high-speed, interactive analysis of both local files and remote scrip...

RedAmon 6.2.5

An autonomous AI framework that chains reconnaissance, exploitation, and post-exploitation into a single pipeline, then goes further by triaging every finding, implementing code fixes, and opening pull requests on your repository. From first packet to merged patch, with human oversight at every...

RedAmon 6.2.2

An autonomous AI framework that chains reconnaissance, exploitation, and post-exploitation into a single pipeline, then goes further by triaging every finding, implementing code fixes, and opening pull requests on your repository. From first packet to merged patch, with human oversight at every...

RedAmon 6.0.2

An autonomous AI framework that chains reconnaissance, exploitation, and post-exploitation into a single pipeline, then goes further by triaging every finding, implementing code fixes, and opening pull requests on your repository. From first packet to merged patch, with human oversight at every...

PT-2026-60385

Name of the Vulnerable Software and Affected Versions Koel versions prior to 9.7.0 Description An authenticated user can perform a Server-Side Request Forgery SSRF via Subsonic-compatible endpoints. The createInternetRadioStation.view and updateInternetRadioStation.view routes fail to implement t...

Lemur Privilege Escalation: Non-admin role members can rewrite role membership via PUT /api/1/roles/<id>

Summary The PUT /api/1/roles/ handler in lemur/roles/views.py gates only on RoleMemberPermissionroleid.can, which is satisfied for any user who is already a member of the target role. The handler then passes data"users" and data"name" directly to service.update, permitting any role member to...

PT-2026-59246

Summary The PUT /api/1/roles/ handler in lemur/roles/views.py gates only on RoleMemberPermissionrole id.can, which is satisfied for any user who is already a member of the target role. The handler then passes data"users" and data"name" directly to service.update, permitting any role member to...

Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability

Large language models LLMs have transformed misinformation from a primarily content-centric problem into a broader ecosystem-level security challenge. When misused, LLMs create risks beyond false content generation, enabling attacks on the social contexts, evidence sources, retrieval corpora, and...

Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety

Large language models LLMs can be induced to produce harmful content through multi turn strategies in which no single user message appears clearly unsafe. Existing runtime safeguards commonly evaluate prompts or responses as isolated messages, which limits their ability to recover ac-cumulated...

RedAmon 5.1.0

An autonomous AI framework that chains reconnaissance, exploitation, and post-exploitation into a single pipeline, then goes further by triaging every finding, implementing code fixes, and opening pull requests on your repository. From first packet to merged patch, with human oversight at every...

Lemur Privilege Escalation: Non-admin role members can rewrite role membership via PUT /api/1/roles/<id>

Summary The PUT /api/1/roles/ handler in lemur/roles/views.py gates only on RoleMemberPermissionroleid.can, which is satisfied for any user who is already a member of the target role. The handler then passes data"users" and data"name" directly to service.update, permitting any role member to...

State of Agentic AI Security and Governance

An OWASP white paper analyzing the security, governance, and risk management considerations surrounding agentic AI systems, including autonomous decision-making, tool access, prompt injection, data protection, and organizational oversight. This is version 2.01...