Tag: llm jailbreaking

1 Attack Reports | 0 Vulnerabilities

Attack reports

How attackers are jailbreaking LLMs with CTF framing and how to catch them

Threat actors are bypassing AI model safety guardrails by framing exploit requests as legitimate security research, such as capture-the-flag challenges or CVE-hunting exercises. This technique manipulates upstream LLMs into generating working exploit code that attackers deploy against real targets.…
credential harvesting
CVE-2026-33017
CVE-2026-39987
ai agent exploitation
CVE-2026-40281
CVE-2026-42208
CVE-2026-42271
CVE-2026-44336
CVE-2026-44694
CVE-2026-42266
CVE-2026-42589
CVE-2026-45331
CVE-2026-45397
CVE-2026-45672
CVE-2026-45301
2026-06-15
ai platform targeting
ctf framing
cve exploitation
CVE-2026-42302
CVE-2026-47391
llm jailbreaking
prompt injection
rce campaigns
Published: June 15, 2026
Linked vulnerabilities : CVE-2026-0770 (CVSS 9.8), CVE-2026-33017 (CVSS 9.3), CVE-2026-39987 (CVSS 9.3), CVE-2026-40281 (CVSS 10.0), CVE-2026-42208 (CVSS 9.3), CVE-2026-42271 (CVSS 8.7), CVE-2026-44336 (CVSS 9.4), CVE-2026-44694 (CVSS 7.2), CVE-2026-42589 (CVSS 9.8), CVE-2026-45331 (CVSS 8.5), CVE-2026-45672 (CVSS 8.8), CVE-2026-45301 (CVSS 8.1), CVE-2026-47391
Downloadable IOCs: 6
Click here to see more Attack Reports