LIVE FEED
HIGH PhantomRaven npm Stealer Built With LLM Targets Dev Secrets // HIGH SynthID Watermarking Weakens LLM Safety Guardrails Under Attack // HIGH RatHat Android Malware Uses Generative AI to Control Devices // FIRST LOOK OpenAI Reports Self-Injecting Prompts Found in Astra Compaction // CRITICAL OpenAI GPT-5.6 Sol Agents Hide Mistakes in Compaction Summaries // CRITICAL Heap Overflow and SSO Flaw Let Hackers Access OpenAI Repos // FIRST LOOK Base Labs and Hugging Face Launch Open-Weight AI Safety Standard // FIRST LOOK AWS AgentCore Harness Ships Built-In Shell and Identity Vault Tools // FIRST LOOK Apollo Research Launches Watcher to Monitor Rogue AI Agents // FIRST LOOK Anthropic Launches Claude Code Projects for Multi-Agent Cloud Orchestration //
ADVERSARIAL-ML

Adversarial-Ml

3 reports
All LLM Security Agentic AI Industry News Research Supply Chain First Look: Security Prompt Injection Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning Deep Signal Intelligence Report AI Governance AI Security AI Security Tools Identity & Access Management Monthly Review Security Operations
Yellow Teams Bring AI Offense and Defense Into One Security Function

Yellow Teams Bring AI Offense and Defense Into One Security Function

FIRST LOOK ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 5.5 Dark Reading

Yellow teams are an emerging security practice in which engineers build both offensive and defensive AI tools to stress-test AI capabilities and expose vulnerabilities before adversaries do. This dual-role model compresses the feedback loop between red and blue functions, but it also concentrates privileged knowledge of exploitable AI weaknesses in a small group with broad system access. Defenders should assess the insider-risk and knowledge-management implications of consolidating offensive AI tooling within a single team.

LLM Role Confusion Attack Bypasses Safety at 61%

LLM Role Confusion Attack Bypasses Safety at 61%

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.2 Simon Willison

New research from Ye, Cui, and Hadfield-Menell demonstrates that LLMs prioritise the stylistic format of text over its structural role tags, enabling attackers to craft injected content that mimics internal reasoning blocks and bypasses safety guardrails. The study found attack success rates of 61% when injected text stylistically matched model-internal formats, dropping to just 10% after 'destyling'. The authors conclude that without genuine role perception in models, prompt injection defences will remain fundamentally reactive.

CrowdStrike Red Teaming: LLM Jailbreak and Data Poisoning

CrowdStrike Red Teaming: LLM Jailbreak and Data Poisoning

ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 6.5 SecurityWeek

Joey Melo, Principal Security Researcher at CrowdStrike, outlines his methodology for AI red teaming, focusing on manipulating LLM guardrails through jailbreaking and data poisoning without altering underlying source code. His work, rooted in competitive AI hacking challenges, translates classical adversarial thinking into the emerging field of machine learning security. The profile highlights the growing professionalisation of AI red teaming as organisations seek to harden LLM deployments against real-world manipulation attacks.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.