Monthly, February 2026
Reconstructed on 19 November 2026 from archived source metadata.
From the editor
The editor's note for this issue is not available. The developments below were selected and ranked automatically from the sources listed.
Top developments
- 1
Google patches first Chrome zero-day exploited in attacks this year
Google has released emergency updates to fix a high-severity Chrome vulnerability exploited in zero-day attacks, marking the first such security flaw patched since the start of the year.
- 2
Microsoft Patch Tuesday matches last year’s zero-day high with six actively exploited vulnerabilities
Microsoft said three of the exploited vulnerabilities were publicly known, suggesting attackers already had details about the defects prior to Tuesday’s release.
- 3
CISA flags critical SolarWinds RCE flaw as exploited in attacks
CISA has flagged a critical SolarWinds Web Help Desk vulnerability as actively exploited in attacks and ordered federal agencies to patch their systems within three days.
- 4
CISA: Recently patched RoundCube flaws now exploited in attacks
CISA flagged two Roundcube Webmail vulnerabilities as actively exploited in attacks and ordered U.S. federal agencies to patch them within three weeks.
- 5
CISA orders feds to patch actively exploited Dell flaw within 3 days
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) ordered government agencies to patch their systems within three days against a maximum-severity Dell vulnerability that has been under active exploitation since mid-2024.
- 6
Critical SolarWinds Serv-U flaws offer root access to servers
SolarWinds has patched four critical Serv-U remote code execution vulnerabilities that could grant attackers root access to unpatched servers.
- 7
Detecting backdoored language models at scale
We’re releasing new research on detecting backdoors in open-weight language models and highlighting a practical scanner designed to detect backdoored models at scale and improve overall trust in AI systems.
- 8
CISA warns of five-year-old GitLab flaw exploited in attacks
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) ordered government agencies to patch their systems against a five-year-old GitLab vulnerability that is actively being exploited in attacks.
- 9
Google says hackers are abusing Gemini AI for all attacks stages
Google Threat Intelligence Group (GTIG) has published a new report warning about AI model extraction/distillation attacks, in which private-sector firms and researchers use legitimate API access to systematically probe models and replicate their logic and reasoning.
- 10
Manipulating AI memory for profit: The rise of AI Recommendation Poisoning
That helpful “Summarize with AI” button? It might be secretly manipulating what your AI recommends. Microsoft security researchers have discovered a growing trend of AI memory poisoning attacks used for promotional purposes, a technique we call AI Recommendation Poisoning.
Further reading, by topic
SAST
- 11
- 12
- 13
- 14
- 15
SCA
- 16
- 17
- 18
- 19
- 20
DAST
- 21
- 22
- 23
- 24
- 25
Agentic SDLC
- 26
- 27
- 28
- 29
- 30
AI-BOM
- 31
Remediation
- 32
- 33
- 34
- 35
- 36
Trust
- 37
- 38
- 39
- 40
- 41
Models
- 42
- 43
- 44
- 45
- 46
AI Security
- 47
- 48
- 49
- 50
- 51
Advisories in this window
- 508 npm advisories300 critical · 105 high · 86 moderate · 17 low
- 147 Go advisories13 critical · 58 high · 63 moderate · 13 low
- 110 PyPI advisories15 critical · 36 high · 49 moderate · 10 low
- 90 Packagist advisories5 critical · 33 high · 43 moderate · 9 low
- 40 Maven advisories4 critical · 10 high · 15 moderate · 11 low
- 39 crates.io advisories10 critical · 11 high · 15 moderate · 3 low
- 39 NuGet advisories9 high · 24 moderate · 6 low
- 11 RubyGems advisories8 high · 2 moderate · 1 low
- 4 Multi-ecosystem advisories2 critical · 1 high · 1 moderate
- 3 GitHub Actions advisories1 high · 2 moderate
- 1 Swift advisory1 moderate
This edition
550 developments and 992 advisories in the window. Selection and order are automatic: how stories are placed and ranked.