agentwatch

agentwatch Claude Code 세션용 비행 기록기입니다. Claude Code를 머신에서 실행하게 놔두세요 — 때로는 몇 시간, 때로는 자동 승인으로. agentwatch는 모든 작업을 조용히 기록하여, 나중에 돌아와 정확히 무슨 일이 일어났는지 확인할 수 있습니다. npm install -g agentwatch-dev agentwatch install 그게 다입니다. 두 개의 명령어입니다. agentwatch는 이제 모든 Claude Code 세션을 기록하고 있습니다. 실제로 사용할 명령어들 agentwatch...

HARDE

HARDE: ランタイムリスク検出と実行制御のためのエージェントハーネス最適化 HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control のコードリリース。 このリポジトリには、2つの相補的なエントリポイントファミリーが含まれています： domains/: Meta-Harness ベースラインと、各ベンチマーク向け HARDE の2つのステージ。 personalizedharness/:...

Malicious code in risk-detection (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 4b74a904a25687bbc34ad321ea019c5083f9a3651457750ed36207a209798f77 package.json declares a dependency ltidisafe whose source is an off-registry tarball URL...

MAL-2026-17563 Malicious code in risk-detection (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 4b74a904a25687bbc34ad321ea019c5083f9a3651457750ed36207a209798f77 package.json declares a dependency ltidisafe whose source is an off-registry tarball URL...

krane

Krane Kubernetes RBAC Analysis made Easy Krane is a simple Kubernetes RBAC static analysis tool. It identifies potential security risks in K8s RBAC design and makes suggestions on how to mitigate them. Krane dashboard presents current RBAC security posture and lets you navigate through its...

HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control

Large language model LLM agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtime defenses that prevent unsafe action in execution across diverse risks while preserving benign-task utility. Existing system-level defenses either...

AURA-Eval: Evaluation Framework for Acting under Risk Awareness in LLM Agent Trajectories

LLM agents operate in workflows where unsafe actions can have real consequences. Existing safety evaluations often reduce behavior to a single score, obscuring risk recognition, pre-action detection, and safe task completion when a safe solution exists. We introduce AURA-Eval, a framework combini...

Qualys Introduces Real-Time Cloud Security Posture Management (CSPM) for Faster Risk Detection and Remediation

Key Takeaways Cloud environments change continuously, while security still relies on periodic scans, leaving gaps where risks go undetected. That gap becomes exposure. Qualys Real-Time CSPM monitors cloud changes as they happen, while still supporting periodic scans for environments that require...

Wiz ASM for any environment, any risk, everywhere

Protect the modern attack surface with new auto-reconnaissance capabilities, deep internal context, and the Red Agent to find any risk, anywhere...

Securing AI Applications From Inception to Deployment

Extending the Wiz AI APP into the code layer to detect AI-specific risks at inception, validate exploitability at runtime, and orchestrate remediation with agents that understand your codebase...

Observability for AI Systems: Strengthening visibility for proactive risk detection

Adoption of Generative AI GenAI and agentic AI has accelerated from experimentation into real enterprise deployments. What began with copilots and chat interfaces has quickly evolved into powerful business systems that autonomously interact with sensitive data, call external APIs, connect to...

Observability for AI Systems: Strengthening visibility for proactive risk detection

Adoption of Generative AI GenAI and agentic AI has accelerated from experimentation into real enterprise deployments. What began with copilots and chat interfaces has quickly evolved into powerful business systems that autonomously interact with sensitive data, call external APIs, connect to...

Scale AI Securely with Qualys TotalAI’s Streamlined Onboarding, Deeper Risk Detection, and Compliance-Ready Reporting

Executive Summary Enterprises are entering a phase where AI systems function as decision engines that shape customer interactions, operational workflows, and business outcomes. This creates a new class of risk that is behavioral, contextual, and dynamic, driven by how models interpret instruction...

CVE-2025-27389

A flaw exists in the verification of application installation sources within ColorOS. Under specific conditions, this issue may cause the risk detection mechanism to fail, which could allow malicious applications to be installed without proper warning...

CVE-2025-27389

Technical details such as affected products, versions, root cause, or exploitation steps are not publicly provided in the supplied documents. Monitor for updates from vendors and CVE feeds.

CVE-2025-27389 Application Installation Source Verification Flaw May Lead to Risk Detection Bypass

A flaw exists in the verification of application installation sources within ColorOS. Under specific conditions, this issue may cause the risk detection mechanism to fail, which could allow malicious applications to be installed without proper warning...

CVE-2025-27389 Application Installation Source Verification Flaw May Lead to Risk Detection Bypass

A flaw exists in the verification of application installation sources within ColorOS. Under specific conditions, this issue may cause the risk detection mechanism to fail, which could allow malicious applications to be installed without proper warning...

EUVD-2025-201354

A flaw exists in the verification of application installation sources within ColorOS. Under specific conditions, this issue may cause the risk detection mechanism to fail, which could allow malicious applications to be installed without proper warning...

CVE-2025-27389: Authentication Bypass by Spoofing

A flaw exists in the verification of application installation sources within ColorOS. Under specific conditions, this issue may cause the risk detection mechanism to fail, which could allow malicious applications to be installed without proper warning...

PT-2025-49188

Name of the Vulnerable Software and Affected Versions ColorOS affected versions not specified Description A flaw exists in the verification of application installation sources within ColorOS. This issue may cause the risk detection mechanism to fail under specific conditions, potentially allowing...