SecAlerts
deepseek logo

deepseek

Security Risk Profile

51
/100
medium

Security Risk Score

Comprehensive risk assessment based on 15 vulnerabilities, EPSS scores, exploitation status, and remediation availability.

📅 Data spans from January 27, 2025 to present

15
Total CVEs
1
Critical+High
7
Exploited
1
Unpatched

Threat Assessment

Avg CVSS
7.5
Base severity
Avg EPSS
0%
Exploit probability
Unpatched
1
Critical/High
Risk Level
51/100
medium
⚠️ 7 Active Exploits

Severity Distribution

Critical
0
High
1
Medium
1
Low
0

Exploit Likelihood

>50% chance
0
20-50%
0
5-20%
0
<5%
0

Age Distribution

Common Weaknesses (CWE)

1
XSS
2

Most Affected Products

1. DeepSeek R16
2. DeepSeek DeepSeek-R15
3. DeepSeek DeepSeek-V35
4. DeepSeek DeepSeek4
5. DeepSeek DeepSeek R14

Recent Vulnerabilities

See more →
https://www.zdnet.com/article/microsoft-obliterated-ai-safety-guardrails-with-one-prompt/
unknown

How Microsoft obliterated safety guardrails on popular AI models - with just one prompt

2/9/2026🔧 No Patch
CVE-2025-63872
CVSS 6.1medium
12/2/2025🔧 No Patch
https://www.theregister.com/2025/11/11/llm_sidechannel_attack_microsoft_researcher/
unknown

LLM side-channel attack could allow snoops to guess topic

11/11/2025⚠ Exploited🔧 No Patch
CVE-2025-26210
CVSS 8.8high
9/3/2025🔧 No Patch
https://www.bleepingcomputer.com/news/security/data-stealing-chrome-extensions-impersonate-fortinet-youtube-vpns/
unknown

Data-stealing Chrome extensions impersonate Fortinet, YouTube, VPNs

5/21/2025⚠ Exploited🔧 No Patch
https://www.zdnet.com/article/how-a-researcher-with-no-malware-coding-skills-tricked-ai-into-creating-chrome-infostealers/
unknown

How a researcher with no malware-coding skills tricked AI into creating Chrome infostealers

3/18/2025⚠ Exploited🔧 No Patch
https://www.zdnet.com/article/ai-chatbots-can-be-hijacked-to-steal-chrome-passwords-new-research-exposes-flaw/
unknown

AI chatbots can be hijacked to steal Chrome passwords - new research exposes flaw

3/18/2025🔧 No Patch
https://www.theregister.com/2025/02/25/chain_of_thought_jailbreaking/
unknown

How nice that state-of-the-art LLMs reveal their reasoning ... for miscreants to exploit

2/25/2025⚠ Exploited🔧 No Patch
https://www.darkreading.com/application-security/llm-hijackers-deepseek-api-keys
unknown

LLM Hijackers Quickly Incorporate DeepSeek API Keys

2/7/2025⚠ Exploited🔧 No Patch
https://www.bleepingcomputer.com/news/security/google-says-hackers-abuse-gemini-ai-to-empower-their-attacks/
unknown

Google says hackers abuse Gemini AI to empower their attacks

2/1/2025🔧 No Patch

Monitor deepseek in Real-Time

Get instant alerts when new vulnerabilities are discovered. Stay ahead of security threats with SecAlerts.

Powered bySecAlerts

Monitor Your Software Stack in Real-Time

Get instant alerts when vulnerabilities are discovered in your software stack. Stay ahead of security threats with SecAlerts.

© 2026 SecAlerts Pty Ltd. All rights reserved.