CVE-2026-61732
Received Received - Intake

Command Injection in Decepticon Autonomous Hacking Agent

Publication date: 2026-09-24

Last updated on: 2026-09-24

Assigner: GitHub, Inc.

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.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-09-24
Last Modified
2026-09-24
Generated
2026-09-24
AI Q&A
2026-09-24
EPSS Evaluated
N/A
NVD
CVE-2026-61732
EUVD
EUVD-2026-86329

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
decepticon decepticon to 1.1.17 (exc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-74 The product constructs all or part of a command, data structure, or record using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify how it is parsed or interpreted when it is sent to a downstream component.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

Decepticon is an autonomous hacking tool for red teams. Versions before 1.1.17 fail to sanitize ChatML special-token literals in web crawl results. Attackers can inject strings into target web pages that forge new operator turns in the LLM, bypassing agent guardrails and executing arbitrary commands in the Kali Linux sandbox.

Impact Analysis

An attacker could exploit this to execute arbitrary commands inside the Kali Linux sandbox where Decepticon runs. This could lead to full system compromise, data theft, or further network infiltration depending on the sandbox permissions.

Compliance Impact

This vulnerability could lead to unauthorized command execution, potentially violating data protection requirements under GDPR (e.g., unauthorized access to personal data) and HIPAA (e.g., unauthorized access to protected health information). Compliance may be compromised if sensitive data is exposed or altered.

Mitigation Strategies

Update Decepticon to version 1.1.17 or later to patch the vulnerability. Ensure your LLM provider filters ChatML special-token literals in default configurations.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-61732. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart