SOURCE-LINKED INTELLIGENCE
CVE-2026-61732: Decepticon is an autonomous hacking agent for red teams. Versions prior to 1.1.17 wrap web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML specia
Decepticon is an autonomous hacking agent for red teams. Versions prior to 1.1.17 wrap web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK (Bring Your Own Key) deployment model, users configure their own LLM credentials to any OpenAI-compatible endpoint. Most open-source and self-deployed model providers (vLLM, SGLang, Ollama, LM Studio, text-generation-webui, etc.) do not filter special-token literals from user content in their default configurations. Those literals are parsed int
Read original source ↗ Open in workspace
- recordType
- vulnerability
- status
- active
- evidenceStatus
- reported
- region
- Global
Evidence & attribution
- NIST National Vulnerability Database · 2026-09-24T00:00:00.000Z
First collected: 2026-09-24T21:32:30.537Z. This is not the publication date.