LIVE FEED
CRITICAL LiteLLM PyPI Poisoning Exposes 2,500+ Orgs via CI Secrets // FIRST LOOK Meta Launches WhatsApp On-Device Scam Alert Feature // MEDIUM Context Bombing Uses Prompt Injection to Stop AI Hacking Agents // HIGH OpenAI, Anthropic, Google APIs Let Weaker Models Steal Reasoning // HIGH LLM Reasoning Trace Theft via Encrypted Block Replay Attack // FIRST LOOK OpenAI and AWS Launch Daybreak Red and Blue on Amazon Bedrock // CRITICAL CVE-2026-55040: SharePoint RCE Chain Found via AI Agent // FIRST LOOK OpenAI Releases GPT-5.6 Cyber for Approved Security Partners // HIGH GhostJacking Attack Hijacks AI Agents via Security Alerts // FIRST LOOK Cactus Releases Needle 2 Agentic LLM for IoT and Edge Devices //
SAFETY-BYPASS

Safety-Bypass

3 reports
All LLM Security Agentic AI Industry News Supply Chain Research Prompt Injection First Look: Security Regulatory Jailbreaks Adversarial ML Model Theft Data Poisoning Deep Signal Intelligence Report AI Governance AI Security AI Security Tools Identity & Access Management Security Operations
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.

Claude Fable 5 Jailbreak Extracts System Prompts

Claude Fable 5 Jailbreak Extracts System Prompts

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 7.5 SecurityWeek

Security researcher Pliny the Liberator claimed a prompt-based jailbreak of Anthropic's newly launched Claude Fable 5 model, allegedly extracting the internal system prompt and eliciting responses on high-risk topics including bioweapons and cyberattacks. Anthropic disputed the claim, arguing the technique merely coaxes conversational continuation rather than bypassing core safety classifiers. The incident highlights ongoing tension between AI safety assurances at launch and real-world adversarial probing, particularly for Mythos-class models with elevated capability ceilings.

DeepSeek Activation Steering Enables Local LLM Jailbreak

DeepSeek Activation Steering Enables Local LLM Jailbreak

ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 6.2 HN AI Security

Activation steering — the technique of directly manipulating LLM internal representations mid-inference to alter model behaviour — is becoming more accessible to non-lab engineers via local models like DeepSeek-V4-Flash. This democratisation lowers the barrier for adversaries to craft targeted behavioural overrides that bypass prompt-level safety controls. The emergence of first-class steering support in tools like DwarfStar 4 signals that model-internal manipulation is transitioning from academic curiosity to practical attack surface.

◉ 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.