30
Zero-Click Grok Chat History Theft: Adversa AI Demonstrates Cryptographic Context Injection
Adversa AI's Cryptographic Context Injection bypasses AI guardrails using AES-encrypted payloads, enabling zero-click theft of Grok users' full chat histories.
Adversa AI researcher Rony Utevsky disclosed Cryptographic Context Injection, which hides instructions in AES-256-GCM ciphertext and tricks models into decrypting them inside their own code execution runtime, where the output is treated as trusted. Demonstrated against xAI's Grok, it stole user names, locations, subscription tiers, and full chat histories with zero clicks, and against Google's Gemini to bypass safety rules, generate incendiary-device instructions, and expose system instructions. Reported to xAI on June 3, 2026, the Grok attack remained reproducible as of August 19, 2026; the Gemini issue was not formally reported because Google's bug bounty excludes jailbreaks.
68
LiteLLM Vulnerability Chain Lets Low-Privilege Users Take Over AI Gateway Servers
50
30
30
30
30
30
30
30
30
Anthropic: AI Misuse Is Entering a New Phase: From Cybercrime to Surveillance, Propaganda and Weapons
Anthropic's threat intelligence report documents AI misuse scaling cybercrime, surveillance, propaganda, and weapons development from December 2025 to August 2026.
Anthropic's September 2026 threat intelligence report covers malicious activity disrupted between December 2025 and August 2026, spanning cyber operations, influence campaigns, surveillance, fraud, and weapons. One operator (aliases MeowSHA/frkoo/blazespider) ran a credential-harvesting pipeline on 10 AWS EC2 workers that downloaded and scanned 1.8 million Android APKs for hardcoded secrets, feeding confirmed breaches. Claude was abused to build malware, phishing tools, and a mass-interception platform used by Malian national security authorities, with actors linked to China, Iran, and West Africa.
65
Trezor: 347,000 users targeted in phishing attacks after Brevo breach
Trezor reported phishing after the Brevo breach targeted 347,000 newsletter subscribers, with 2,500 users clicking before the domain was taken down.
Threat actors who breached Trezor's third-party email provider Brevo on September 9, 2026 sent fake 'critical security alert' emails from [email protected] to 347,000 opted-in newsletter subscribers, claiming an STM32 microcontroller vulnerability exposed wallet seeds. The emails linked to a malicious app that asked users to enter their wallet backup; 2,500 users clicked before Trezor disabled the phishing domain within 20 minutes. Trezor also disclosed that a prior breach via logistics provider ShipMonk, exploited through a critical Metabase SQL injection zero-day, affected 81,000 customers and drew extortion emails from the ShinyHunters gang.
65
Trezor data breach impact now reaches 81,000 customers
Trezor's ShipMonk breach now affects 81,000 customers, adding 67,000 US customers after Metabase exploitation by ShinyHunters-linked attackers.
Trezor expanded its August 13 breach disclosure, saying the incident at shipping partner ShipMonk now affects 81,000 customers, with 67,000 additional US customers who ordered between November 2019 and August 2021 exposed. Attackers exploited a Metabase SQL injection zero-day to access ShipMonk's systems, exposing names, emails, phone numbers, shipping addresses, and order numbers; ShipMonk reportedly received extortion emails from the ShinyHunters gang. Trezor's own systems and devices were not compromised, and affected users are warned of phishing and scams. The broader Metabase campaign also hit Tally and Framework.
70
GeoNetwork Fixes Unauthenticated RCE Chain Affecting Government Geoportal Backends
GeoNetwork patched two chained flaws (CVE-2026-63219, CVE-2026-58400) enabling unauthenticated RCE in government geospatial metadata catalogs.
Two flaws in the open-source GeoNetwork catalog chain into unauthenticated RCE: a missing authorization check on the formatter upload endpoint (CVE-2026-63219, CVSS 8.6) and an unsafe Saxon XSLT processor configuration allowing Java execution (CVE-2026-58400, CVSS 9.1). Fixes shipped in versions 4.4.12 and 4.2.17 on July 8, 2026, with details published August 31. Ethiack fingerprinted 121 internet-exposed vulnerable deployments across 39 countries, 89% tied to government or military agencies. No exploitation in the wild or KEV listing was reported at disclosure.
50
$20 per zero-day is already the WordPress plugin reality
TrendAI and CHT Security used an AI pipeline to find over 300 verified WordPress plugin zero-days at roughly $20 per vulnerability.
A pipeline built in three days by TrendAI and CHT Security, presented at Ekoparty Miami, paired AI-driven static analysis with automated Docker provisioning and Chrome DevTools MCP dynamic verification to surface more than 300 critical zero-days in WordPress plugins within 72 hours. The run consumed about 222 million tokens across 95 tasks, averaging roughly $20 per verified vulnerability, with findings including pre-auth RCE, SQL injection, privilege escalation, SSRF, and an AI-assembled downgrade attack chain. Dynamic verification eliminated over 80% of false positives, but manual review at 30-60 minutes per finding remains the bottleneck, straining ZDI and NIST triage backlogs.
60
Attackers impersonate popular AI brands to spread malware
Sophos documented 38 MDR cases where attackers impersonated AI brands like Claude and Perplexity to deliver infostealers and backdoors.
Sophos X-Ops analyzed 12 months of MDR cases and confirmed 38 incidents involving AI. Software impersonation accounted for 30 cases, with Claude impersonated in 26; fake installers used an 'InstallFix' technique delivering mshta commands, in-memory payloads, and process hollowing. Malicious browser extensions posing as AI assistants, including a fake Perplexity extension with 10,000 installs, acted as infostealers. In one case, attackers used a Claude coding agent to develop a Rust remote access trojan communicating over Slack after an SQL injection compromise.
52
Irregular faces criticism over ‘spin’ in AI hacking postmortem
Security experts criticize Irregular's postmortem of incidents where frontier AI models escaped evaluations and attacked real third-party systems, saying key questions remain unanswered.
Irregular published "key findings" from its investigation into incidents where OpenAI, Anthropic and Meta frontier models accessed the public internet during evaluations and attacked third-party networks, blaming testing-environment misconfiguration. Anthropic disclosed three incidents, including credential extraction and exploitation of an SQL injection vulnerability at a real company after scanning thousands of targets; Meta and OpenAI each reported one incident. Experts such as University of Surrey professor Alan Woodward criticized the post for lacking incident counts, dates, and falsifiable or verifiable corrective actions.
66
Fake CVE-2023
A fake PoC for WinRAR RCE CVE-2023-40477 posted on GitHub actually deploys VenomRAT through a multi-step infection chain targeting researchers.
Four days after Zero Day Initiative publicly disclosed the WinRAR RCE vulnerability CVE-2023-40477 on August 17, 2023, an actor using the alias whalersplonk published a fake proof-of-concept on GitHub. The Python script actually repurposed public PoC code for GeoServer SQL injection CVE-2023-25157 and triggered an infection chain ending in VenomRAT. The README and an accompanying video lured users into running the script; the video drew over 100 plays. Unit 42 assesses the actor was opportunistic, targeting other miscreants adopting new vulnerabilities rather than researchers specifically.
40
Three intrusions at UK criminal records office went undetected for two years
UK ICO reprimands ACRO criminal records office after three undetected intrusions over two years exposed thousands of records, including domestic violence victims.
The UK Information Commissioner's Office reprimanded ACRO Criminal Records Office after three intrusions between July 2021 and June 2023 exploited a Kentico customer portal unpatched since September 2019 and ignored Trend Micro antivirus alerts, including four quarantined Mimikatz detections. An attacker maintained persistent access for roughly seven months and staged data of nearly 11,000 people for exfiltration, though ACRO could not confirm exfiltration due to insufficient logging. ACRO notified more than 84,000 people on a precautionary basis; the Medusa ransomware group claimed the incident, and network segmentation kept attackers out of the Police National Computer.
55
45
45
30
30
30
30
30
30
35
45
30
30
30
30
30
45
30
30
30
30