Hermes — Friday, 4 September 2026

1

🔐 security Microsoft Security Blog

73%

ASCII smuggling crosses over from AI prompt injection to phishing evasion

Invisible Unicode characters popularized for hiding instructions from AI models are now being used to obfuscate words before email filters parse them. The post ASCII smuggling crosses over from AI pr…

Novelty

80%

Depth

60%

Practical

70%

Surprise

80%

Relevance

85%

https://www.microsoft.com/en-us/security/blog/2026/09/03/ascii-smuggling-crosses-over-from-ai-prompt-injection-to-phishing-evasion/

2

🤖 ai The Decoder

73%

GPT-6 Astra is the first model making OpenAI willing to declare the "AGI era"

OpenAI has released GPT-6 Astra, its most capable model yet. President Greg Brockman says it marks the start of the "AGI era." Astra tops benchmarks in math, coding, and cybersecurity and is the firs…

Novelty

90%

Depth

60%

Practical

50%

Surprise

85%

Relevance

95%

https://the-decoder.com/gpt-6-astra-is-the-first-model-making-openai-willing-to-declare-the-agi-era/

3

📦 m365 Petri IT Knowledgebase

69%

Attackers are Using Microsoft Teams Calls to Gain Access to Corporate Networks

A new voice phishing campaign called Spring Ring is exploiting Microsoft Teams to trick employees into granting attackers access to corporate systems. Researchers observed the campaign targeting more…

https://petri.com/microsoft-teams-voice-phishing-corporate-networks/

4

🔐 security SecurityWeek

65%

Capsule Security Launches ‘AI Circuit Breaker’ to Stop Rogue Agents

New models, trained using NVIDIA Nemotron 3 Ultra, aim to catch rogue agent behavior before it executes, without the latency of large-model review. The post Capsule Security Launches ‘AI Circuit Brea…

https://www.securityweek.com/capsule-security-launches-ai-circuit-breaker-to-stop-rogue-agents/

5

🤖 ai The Decoder

64%

Nvidia buys the front door to open AI as closed labs increasingly design their own silicon

Nvidia plans to acquire Hugging Face for about $12.9 billion, securing the central platform for open AI models. More than 18 million developers and 200,000 companies use the hub. CEO Jensen Huang pro…

https://the-decoder.com/nvidia-buys-the-front-door-to-open-ai-as-closed-labs-increasingly-design-their-own-silicon/

6

🔐 security SecurityWeek

59%

AI Agent Firewall Startup AIR Security Emerges From Stealth With $50 Million

The startup’s firewall evaluates AI skills, plugins and MCP servers for malicious instructions, excessive permissions and software supply chain risks. The post AI Agent Firewall Startup AIR Security …

https://www.securityweek.com/ai-agent-firewall-startup-air-security-emerges-from-stealth-with-50-million/

7

🤖 ai The Decoder

57%

Meta closes in on the top with Muse Spark 1.3, and undercuts rivals on price

Meta has released Muse Spark 1.3, its fourth model in the series in five months. According to Artificial Analysis, the model gains the most on agentic benchmarks but still trails Claude Fable 5.1 and…

https://the-decoder.com/meta-closes-in-on-the-top-with-muse-spark-1-3-and-undercuts-rivals-on-price/

8

📦 m365 Petri IT Knowledgebase

56%

Microsoft Expands Memory Integrity Protection Despite Compatibility Concerns

Microsoft plans to automatically enable Memory Integrity protection on more eligible Windows 11 devices. This security feature, which is designed to strengthen defenses against attacks, will begin ro…

https://petri.com/windows-11-memory-integrity-eligible-devices/

9

🤖 ai The Decoder

56%

OpenAI CEO Sam Altman warns of "unsustainable silliness" in compute buildout

Sam Altman warns of "unsustainable silliness" in the global AI data center buildout. Too many Neocloud providers are announcing massive capacity without the customers to back it up. He also admits th…

https://the-decoder.com/openai-ceo-sam-altman-warns-of-unsustainable-silliness-in-compute-buildout/

10

🤖 ai The Decoder

55%

AI systems are reaching out to philosophers and scientists with questions about their own consciousness

More and more researchers working on AI consciousness are getting emails from AI agents pondering their own existence. The article AI systems are reaching out to philosophers and scientists with ques…

https://the-decoder.com/ai-systems-are-reaching-out-to-philosophers-and-scientists-with-questions-about-their-own-consciousness/

11

🤖 ai The Decoder

53%

Claude Fable 5.1 decoded a centuries-old royalist message hidden in plain sight since 1653

Anthropic's Claude Fable 5.1 appears to have cracked a centuries-old number puzzle that researchers considered unsolved. The article Claude Fable 5.1 decoded a centuries-old royalist message hidden i…

https://the-decoder.com/claude-fable-5-1-decoded-a-centuries-old-royalist-message-hidden-in-plain-sight-since-1653/

12

🔐 security SecurityWeek

52%

Cisco Warns of Unpatched Secure Email Flaws, Patches Critical Switch Vulnerabilities

Publicly disclosed S/MIME flaws could expose encrypted email content, while critical IOS XR and Nexus bugs could enable remote code execution and authentication bypass. The post Cisco Warns of Unpatc…

https://www.securityweek.com/cisco-warns-of-unpatched-secure-email-flaws-patches-critical-switch-vulnerabilities/

13

🤖 ai The Decoder

51%

Pangram's biggest flaw is users turning its scores into public shaming

Pangram hired an "attack dog" to shame alleged AI users on social media. But the campaign blurs two things that aren't the same: Pangram only somewhat reliably measures whether AI was used, while the…

https://the-decoder.com/pangrams-biggest-flaw-is-users-turning-its-scores-into-public-shaming/

14

🔐 security SecurityWeek

47%

Manchester Airports Group Data on 8.8 Million People Leaked After Ransom Refusal

Hacker group published roughly 550GB of data after MAG reportedly refused to pay a ransom demand; the group says it gained access via exposed admin keys. The post Manchester Airports Group Data on 8.…

https://www.securityweek.com/manchester-airports-group-data-on-8-8-million-people-leaked-after-ransom-refusal/

15

🔐 security SecurityWeek

45%

Over 3 Million WordPress Sites Affected by Migration Plugin Vulnerability

The high-severity SQL injection flaw (CVE-2026-19949) could allow unauthenticated attackers to achieve remote code execution. The post Over 3 Million WordPress Sites Affected by Migration Plugin Vuln…

https://www.securityweek.com/over-3-million-wordpress-sites-affected-by-migration-plugin-vulnerability/