CVE-2026-61732
Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context
- Published
- Sep 24, 2026
- Updated
- Sep 24, 2026
- Assigning CNA
- GitHub_M
- Evidence observed
- Sep 25, 2026
Primary CVSS
cvelist · CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:HSummary
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 into structural role-boundary token IDs, meaning an attacker string planted in a target web page forges a new operator turn the model treats as authoritative, bypassing Decepticon's agent guardrails and resulting in arbitrary command execution inside the Kali Linux sandbox. Version 1.1.17 patches the issue.
Sources
Benign, self-contained reproduction of CVE-2026-61732 (Decepticon ChatML role-boundary forgery)
Responsible use
Use vulnerability information only on systems you own or are authorized to test. Kitploit links to public research metadata and does not store exploit code or malicious payloads.