CVE-2026-61732
Tenable Plugin
Checking the public Tenable catalog…
Threat Intelligence Pending
IOCs, MITRE ATT&CK techniques, and attack chain data are being generated. Refresh in a few seconds.
Description
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.
Quick Facts
| CVE ID | CVE-2026-61732 |
| CVSS Score | 10.0 |
| Vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H |
| Published | 2026-09-24 |
| Exploited | No |
| CISA KEV | No |
| PoC | Not public |