CWE-1427
26 published CVEs are weaknesses of this kind, as the records or NVD name it.
- Published CVEs
- 26
- Last 12 months
- 20
- Critical
- 2
- Known exploited
- 0
Critical 2High 12Medium 12Low 0Not scored 0
CVEs per yearBy the year they were published
- 20256
- 202620
Newest CVEs
- 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 input
esengine · DeepSeek-Reasonix
Medium5.3 - CVE-2026-54142
OpenHuman: Indirect prompt injection via background email sync executes Composio actions without user approval
tinyhumansai · openhuman
High8.7 - CVE-2026-54140
OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization
tinyhumansai · openhuman
High8.3 - CVE-2026-115415
Secret masking bypass in the environment tool in Strands Agents Tools
amazon · 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 BackgroundRunTool
HKUDS · Vibe-Trading
High8.7 - CVE-2026-109440
LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode
ginlix-ai · LangAlpha
High8.7 - CVE-2026-77931
MoviePilot 3.1.5 Command Injection via ExecuteCommandTool
jxxghp · MoviePilot
High8.7 - CVE-2026-96893
Improper Neutralization of Input Used for LLM Prompting in GitLab
GitLab · GitLab
High7.3 - CVE-2026-70331
Microsoft Edge for iOS Spoofing Vulnerability
Microsoft · Microsoft Edge (Chromium-based)
Medium5.4