AI Threat Alert

OWASP LLM Top 10 Compliance Tracker

The OWASP Top 10 for LLM Applications identifies the most critical security risks for applications using Large Language Models. Each risk category below is mapped to real CVEs affecting AI/ML packages in production.

2692
CVEs Mapped
10
Controls with CVEs
3373
Total Mappings
ISO 42001 EU AI Act NIST AI RMF OWASP LLM Top 10

Controls & Mapped Vulnerabilities

LLM01

Prompt Injection

92 CVEs
CRITICAL
CVE-2026-61447 CVSS 10.0

PraisonAI: RCE via unsandboxed LLM code execution

CRITICAL
CVE-2026-54769 CVSS 10.0

Langroid: prompt injection to RCE via broken eval() sandbox

CRITICAL
CVE-2026-47392 CVSS 9.9

praisonaiagents: RCE via Python sandbox bypass

+ 89 more CVEs mapped to this control

LLM02

Sensitive Information Disclosure

200 CVEs
CRITICAL
CVE-2026-34938 CVSS 10.0

praisonaiagents: sandbox bypass enables full host RCE

CRITICAL
CVE-2026-61447 CVSS 10.0

PraisonAI: RCE via unsandboxed LLM code execution

CRITICAL
CVE-2026-33663 CVSS 10.0

n8n: member role steals plaintext HTTP credentials

+ 197 more CVEs mapped to this control

LLM03

Supply Chain Vulnerabilities

178 CVEs
CRITICAL
CVE-2026-25115 CVSS 9.9

n8n: Protection Bypass circumvents security controls

CRITICAL
CVE-2026-7873 CVSS 9.9

Langflow: authenticated RCE enables credential theft

CRITICAL
CVE-2026-8476 CVSS 9.9

Langflow: pickle deserialization RCE via disk cache (CVSS 9.9)

+ 175 more CVEs mapped to this control

LLM04

Data and Model Poisoning

187 CVEs
CRITICAL
CVE-2025-53002 CVSS 9.8

LLaMA-Factory: RCE via unsafe checkpoint deserialization

CRITICAL
CVE-2026-55450 CVSS 9.3

Langflow: unauthenticated upload → DoS + path disclosure

CRITICAL
CVE-2026-27493 CVSS 9.0

n8n: Code Injection enables RCE

+ 184 more CVEs mapped to this control

LLM05

Improper Output Handling

242 CVEs
CRITICAL
CVE-2026-26030 CVSS 10.0

semantic-kernel: Code Injection enables RCE

CRITICAL
CVE-2025-15379 CVSS 10.0

MLflow: RCE via unsanitized model dependency specs

CRITICAL
CVE-2025-71338 CVSS 10.0

Flowise: unauthenticated file write enables RCE

+ 239 more CVEs mapped to this control

LLM06

Excessive Agency

435 CVEs
CRITICAL
CVE-2026-72811 CVSS 10.0

SiYuan: SQL injection enables cross-notebook DB access

CRITICAL
CVE-2026-46695 CVSS 10.0

Boxlite: read-only bypass enables host code execution

CRITICAL
CVE-2026-33663 CVSS 10.0

n8n: member role steals plaintext HTTP credentials

+ 432 more CVEs mapped to this control

LLM07

System Prompt Leakage

351 CVEs
CRITICAL
CVE-2025-14931 CVSS 10.0

smolagents: RCE via pickle deserialization in executor

CRITICAL
CVE-2026-10134 CVSS 10.0

Langflow: unauthenticated RCE via tool_code injection

CRITICAL
CVE-2026-39888 CVSS 10.0

praisonaiagents: sandbox escape enables host RCE

+ 348 more CVEs mapped to this control

LLM08

Vector and Embedding Weaknesses

321 CVEs
CRITICAL
CVE-2026-61447 CVSS 10.0

PraisonAI: RCE via unsandboxed LLM code execution

CRITICAL
CVE-2026-54769 CVSS 10.0

Langroid: prompt injection to RCE via broken eval() sandbox

CRITICAL
CVE-2025-14931 CVSS 10.0

smolagents: RCE via pickle deserialization in executor

+ 318 more CVEs mapped to this control

LLM09

Misinformation

20 CVEs
CRITICAL
CVE-2024-39236 CVSS 9.8

Gradio: code injection via component metadata (CVSS 9.8)

CRITICAL
CVE-2025-61260 CVSS 9.8

OpenAI Codex CLI: RCE via malicious MCP config files

HIGH
GHSA-m3mh-3mpg-37hw CVSS 8.6

OpenClaw: .npmrc hijack enables RCE on plugin install

+ 17 more CVEs mapped to this control

LLM10

Unbounded Consumption

41 CVEs
HIGH
GHSA-5qw8-f2g9-ff29 CVSS 8.2

PraisonAI: auth bypass exposes recipe API to unauthenticated callers

HIGH
GHSA-52vm-mxx8-f227 CVSS 7.7

Phantom MCP: unconfined output path enables file write

HIGH
CVE-2026-28461 CVSS 7.5

OpenClaw: webhook DoS via memory exhaustion

+ 38 more CVEs mapped to this control

Download Full Evidence Pack

Get the complete OWASP LLM Top 10 evidence pack with all CVE-to-control mappings, rationale, and audit-ready documentation. Exportable as CSV.

Get Evidence Pack