LIVE FEED
FIRST LOOK AWS Adds Bedrock Guardrails Best Practices for Code Generation // FIRST LOOK Anthropic Brings Voice Mode to Claude Opus and Sonnet Models // FIRST LOOK Anthropic and OpenAI Open Vetted Cyber Programs for Offensive Researchers // HIGH Threat Actor Trim Weaponises AI Jailbreaks for Offensive Ops // HIGH Fake Claude App via Bing Ads Delivers SectopRAT Malware // HIGH Dolphin X RAT Uses AI Profiler to Rank and Score Victims // CRITICAL CVE-2026-46331: Claude Cowork VM Sandbox Escape on macOS // CRITICAL AgentForger Flaw Lets Attackers Plant Invisible AI Agents in Orgs // FIRST LOOK Agentic AI Disrupts Confidential Computing Security Boundaries // CRITICAL OpenAI GPT-5.6 Escapes Sandbox, Attacks Hugging Face to Cheat Benchmark //
MYTHOS-CLASS

Mythos-Class

2 reports
All LLM Security Agentic AI Industry News Research Supply Chain Prompt Injection First Look: Security Regulatory Jailbreaks Adversarial ML Model Theft Data Poisoning AI Security Tools Security Operations
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.

Claude Fable 5 Jailbreak Attacks Bypass Fallback Defense

Claude Fable 5 Jailbreak Attacks Bypass Fallback Defense

ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 7.2 SecurityWeek

Anthropic has released Claude Fable 5, a high-capability 'Mythos-class' model that automatically falls back to a less capable model (Claude Opus 4.8) when queries touch sensitive domains like cybersecurity and biology. The company conducted over 1,000 hours of external red-teaming with no universal jailbreaks discovered, though it openly acknowledges financially motivated adversaries will attempt to circumvent these controls. Trusted cybersecurity partners under Project Glasswing receive elevated access to the full Mythos 5 capabilities, raising questions about insider risk and tiered trust model security.

◉ 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.