Every public CVE, as it is published
The whole CVE List, enriched with NVD scores, CISA's known exploited catalog and EPSS exploit probabilities. Updated every few minutes; last read 4 min ago.
At a glance
Published CVEs; rejected ones are not counted.
- 411,228All CVEsplus 19,197 rejected
- 403Last 24 hours4,630 in the last 7 days
- 16,510Last 30 days1,450 of them critical
- 1,790Known exploitedin the CISA KEV catalog
CVEs published per year
All time, by publication date in UTC; follows the filter above.
- Critical
- High
- Medium
- Low
- Not scored
Show the numbers as a table
| Period | Critical | High | Medium | Low | Not scored | Total | Cumulative |
|---|---|---|---|---|---|---|---|
| 2026 | 2 | 14 | 7 | 1 | 0 | 24 | 30 |
| 2025 | 0 | 0 | 6 | 0 | 0 | 6 | 6 |
| Title | ||
|---|---|---|
| CVE-2026-18883 | Indirect Prompt Injection in Email Response AI Agent (Now Assist for CSM)ServiceNow · Now Assist for CSM | High7.1 |
| CVE-2026-126767 | OpsTree REMS through 1.0.0 Prompt Injection via RCA Chat AssistantPublic exploitOpsTree Solutions · REMS | Medium5.3 |
| CVE-2026-123498 | Vikunja veans before 2.7.1 Prompt Injection via Project and Task Metadatago-vikunja · vikunja | Low2.1 |
| CVE-2026-102344 | Lavish: DNS rebinding allows any website to read arbitrary local files and inject prompts into the AI agent via the unauthenticated local serverPublic exploitkunchenguid · lavish-axi | High8.1 |
| CVE-2026-106020 | Improper neutralization of input used for LLM prompting vulnerability in Johnson Controls EasyIO Neo IO Manager and Tools Installer allows Search Order…Johnson Controls · EasyIO Neo IO Manager and Tools Installer | High8.6 |
| CVE-2026-123653 | esengine DeepSeek-Reasonix doc.go discoverDocs llm prompting inputPublic exploitesengine · DeepSeek-Reasonix | Medium5.3 |
| CVE-2026-54142 | OpenHuman: Indirect prompt injection via background email sync executes Composio actions without user approvalPublic exploittinyhumansai · openhuman | High8.7 |
| CVE-2026-54140 | OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitizationPublic exploittinyhumansai · openhuman | High8.3 |
| CVE-2026-115415 | Secret masking bypass in the environment tool in Strands Agents Toolsamazon · strands-agents-tools | Medium5.9 |
| CVE-2026-114107 | HKUDS Vibe-Trading 0.1.0 before 0.1.7 Indirect Prompt Injection RCE via BashTool and BackgroundRunToolHKUDS · Vibe-Trading | High8.7 |
| CVE-2026-109440 | LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCodePublic exploitginlix-ai · LangAlpha | High8.7 |
| CVE-2026-77931 | MoviePilot 3.1.5 Command Injection via ExecuteCommandTooljxxghp · MoviePilot | High8.7 |
| CVE-2026-96893 | Improper Neutralization of Input Used for LLM Prompting in GitLabGitLab · GitLab | High7.3 |
| CVE-2026-70331 | Microsoft Edge for iOS Spoofing VulnerabilityMicrosoft · Microsoft Edge (Chromium-based) | Medium5.4 |
| CVE-2026-78379 | Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents ToolsAmazon · strands-agents-tools | Critical9.2 |
| CVE-2026-75130 | Context7 2.1.2 Prompt Injection via Custom AI InstructionsPublic exploitUptash · Context7 | Medium6.4 |
| CVE-2026-21832 | HCL AION is affected by multiple security vulnerabilities.HCL Software · AION | Medium4.3 |
| CVE-2026-18733 | Prompt injection bypasses shell tool consent gate in Strands Agents ToolsAWS · strands-agents-tools | High7.5 |
| CVE-2026-15077 | Improper Neutralization of Input Used for LLM Prompting in GitLabGitLab · GitLab | Medium4.3 |
| CVE-2026-46580 | In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or…Eclipse Foundation · Eclipse Theia | High8.4 |
| CVE-2026-44688 | In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing…Eclipse Foundation · Eclipse Theia | High8.4 |
| CVE-2026-44717 | MCP Calculate Server: Prompt Injection to RCE611711Dark · mcp_calculate_server | Critical9.8 |
| CVE-2026-44246 | nnU-Net: Agentic workflow injection in `.github/workflows/issue-triage.yml` of `MIC-DKFZ/nnUNet`Public exploitMIC-DKFZ · nnUNet | High7.2 |
| CVE-2026-4399 | Multiple vulnerabilities in 1millionbot Millie chatbot1millionbot · Millie chat | High8.7 |
| CVE-2025-64321 | Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Agentforce Vibes Extension allows Manipulating Writeable Configuration…Salesforce · Agentforce Vibes Extension | Medium5.3 |
| CVE-2025-64320 | Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Agentforce Vibes Extension allows Code Injection.This issue affects…Salesforce · Agentforce Vibes Extension | Medium6.5 |
| CVE-2025-64318 | Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Mulesoft Anypoint Code Builder allows Manipulating Writeable Configuration…Salesforce · Mulesoft Anypoint Code Builder | Medium5.3 |
| CVE-2025-10875 | Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Mulesoft Anypoint Code Builder allows Code Injection.This issue affects…Salesforce · Mulesoft Anypoint Code Builder | Medium6.5 |
| CVE-2025-36730 | Windsurf Prompt Injection via FilenamePublic exploitWindsurf · Windsurf | Medium4.6 |
| CVE-2024-3303 | Improper Neutralization of Input Used for LLM Prompting in GitLabPublic exploitGitLab · GitLab | Medium6.4 |