AI Threat Alert
Attack Type
Jailbreak
Jailbreaking refers to techniques that bypass safety guardrails and content filters in language models, enabling the generation of harmful, restricted, or policy-violating content.
2
Total CVEs
1
Pages
Page 1 of 1
Current
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| HIGH | CVE-2025-30358 | Mesop: class pollution enables DoS and LLM jailbreak | 8.1 | |
| UNKNOWN | CVE-2026-4399 | 1millionbot Millie: Boolean prompt injection bypasses restrictions | - |