CVE•Published 2026-09-24•Modified 2026-09-30•1 article on news•4 live references•NVD data

CVE-2026-61732

Vulnerability data via NVD (ingested)

CVSS v3.1
10.0
CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
EPSS percentile
67
Exploit Prediction Scoring System · top 33% of all CVEs
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.

Timeline
Published 2026-09-24
Modified 2026-09-30

External references

Search for exposed instances

Shodan + Censys queries derived from NVD's CPE data. The vuln tag catches assets Shodan has explicitly linked to this CVE; the product / banner fingerprints find exposed instances even when the vuln tag was never applied (which is common).

More intel sources (5)

Known PoCs on GitHub

No public proof-of-concept repositories found for CVE-2026-61732 on GitHub.