CVSS

Troubleshooting AI Bug Hunting: Seven Critical Mistakes That Destroy Report Validity

Two Russian researchers shared detailed lessons from six months of running AI agents on domestic bug bounty platforms. The presentation, originally delivered at OFFZONE, covers hallucinations, lack of validation, threat model misunderstandings, severity inflation, bloated reports, high token costs, and scope violations. Vladislav Bek and Daniil Shushakov describe practical fixes including tool-enabled agents, dual-agent verification, strict templates, and cascaded model architectures. They emphasize that AI must execute real commands in isolated environments rather than fabricate results. The speakers also address scaling on private events, handling model refusals, and the continued necessity of human final validation. Their checklist stresses business context, proven impact, and staying within program boundaries to produce accepted, high-value reports.

CTEM Without the Hype: Understanding Gartner's Continuous Threat Exposure Management Framework

The article explains the evolution of vulnerability management from basic scheduled scanning to risk-based approaches and finally to Continuous Threat Exposure Management (CTEM). It positions CTEM as a comprehensive program introduced by Gartner in 2022 that integrates asset management, EASM, CAASM, automated pentesting, and business-context prioritization. The five-stage cycle of Scoping, Discovery, Prioritization, Validation, and Mobilization is detailed with practical examples such as protecting customer databases in an e-commerce environment. Gartner predicts organizations prioritizing CTEM will suffer three times fewer breaches by 2026, though only 16% have reached operational maturity. The piece also covers common implementation pitfalls and the emergence of the first Magic Quadrant for Exposure Assessment Platforms featuring vendors like Tenable, Qualys, and Rapid7.

Fuzzy Logic in Cybersecurity: Reducing Vulnerability Queue by 7.5 Times with CVSS, EPSS and FSTEC Comparison

An information security specialist has developed a fuzzy logic system that prioritizes vulnerabilities far more effectively than traditional scoring methods. The approach uses linguistic variables and membership functions to handle the inherent uncertainty in exploitability and impact assessments. By integrating EPSS probability data with CVSS impact scores and vulnerability age, the model reduces the actionable backlog by a factor of 7.5. The implementation relies on the Mamdani inference algorithm and trapezoidal membership functions to produce smooth, human-interpretable urgency ratings. Detailed coverage checks and rule-base validation ensure no gaps exist in the decision space. Real-world testing on CVE-2025-49113 in Roundcube Webmail demonstrated practical advantages over rigid threshold logic. The method is positioned as a practical enhancement rather than a replacement for existing standards.

Building a Cybersecurity News Aggregator: Story Clustering, Seven Importance Signals and Strict Filtering Thresholds

The idea for an information security news aggregator emerged years ago with the goal of delivering only the most relevant stories while eliminating noise. Early versions relied on the rut5_base_sum_gazeta summarization model and TextRank for importance scoring, but performance remained unsatisfactory. The current system processes roughly one thousand items daily from more than 200 sources and publishes only about 0.5 percent of them. A hybrid approach now combines a transparent seven-feature formula that scores story importance with an LLM that removes irrelevant content and generates concise summaries. The formula incorporates signals such as confirmation count, CVSS severity, exploitation status from KEV, source tier, proximity to Russian readers, depth of analysis, and publication speed. Penalties are applied for vendor self-promotion, webinars, and job postings. Stories are clustered using CVE identifiers, shared trigrams, and named entities to avoid duplicate posts while preserving original reporting.

Cisco Pre-Announces Security Advisories and Patches for Multiple Products on September 2, 2026

Cisco Systems has disclosed plans to publish security advisories for several product lines on September 2, 2026. The advisories will cover vulnerabilities affecting IP telephony devices, network switches, and email security appliances. Targeted products include Cisco IOS XR Software, multiple series of Cisco Desk Phones, Nexus 9000 Series switches with Silicon One, and Cisco Secure Email. The company will also provide updates aimed at strengthening security in IOS XR. No CVE identifiers, vulnerability details, affected versions, or CVSS scores have been released at the pre-notification stage. Cisco strongly recommends applying the forthcoming fixes once they become available, while noting that the schedule and product scope may still change.

Dark Patterns in Vulnerability Management: How Metrics Undermine Real Security

Vulnerability management programs often fail not due to lack of scanners but because of poorly chosen metrics that prioritize reporting over actual risk reduction. Teams focus on closing easy vulnerabilities, meeting CVSS-based deadlines, and improving dashboard numbers while attackers exploit the shortest path to critical assets. The article examines five common traps including total vulnerability counts, context-free SLAs, closure rate targets, static dashboards, and claims of no critical findings. It argues that these metrics create a false sense of security and distort team behavior according to Goodhart's Law. Instead, organizations should adopt attack path metrics, exposure management approaches such as CTEM, and measurements that track real reduction in attacker reachability. The piece highlights MaxPatrol Carbon as an example of tools that model attacker paths rather than isolated CVEs.

OpenClaw AI Assistant Compromised via WhatsApp: Three Critical Vulnerabilities Allowed Credential Theft, Sandbox Escape, and Arbitrary Code Execution on Host

Security researchers discovered three high-severity vulnerabilities in OpenClaw that could let attackers steal credentials, escalate privileges, and execute arbitrary code on the host system running the AI assistant. Two flaws rated 8.8 on the CVSS scale stemmed from incomplete command filtering that failed to block dangerous inputs, while a third issue rated 8.4 enabled sandbox bypass by mounting parent directories such as /home or /var. The weaknesses potentially exposed sensitive data in ~/.ssh, ~/.aws, and ~/.gnupg, and even allowed attackers to reach the Docker socket for full host escape. Notably, the attack could be triggered remotely through an external WhatsApp message without any prior system access, according to researcher Chinmohan Nayak. All issues were patched in OpenClaw version 2026.6.6, and users are urged to update immediately while tightening sandbox and tool permissions.