1. Home
  2. Vulnerabilities
  3. CVE-2026-61732
10.0
CRITICAL CVSS 3.1
CVE-2026-61732
Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context
Overview
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.

Details
INFO

Published Date :

Sept. 24, 2026, 6:17 p.m.

Last Modified :

Sept. 30, 2026, 5:32 p.m.

Remotely Exploit :

Yes !

Source :

[email protected]
Impact
Affected Products

The following products are affected by CVE-2026-61732 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

ID Vendor Product Action
1 Bittersecurity decepticon
2 Bittersecurity decepticon-core
3 Bittersecurity decepticon-sdk
: Total Affected Vendor : 1 | Products : 3
Scoring
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 134c704f-9b21-4f2e-91b3-4a467353bcc0
CVSS 3.1 CRITICAL [email protected]
Solution
Update Decepticon to version 1.1.17 or later to address arbitrary command execution.
  • Update Decepticon to version 1.1.17.
  • Ensure LLM endpoint filters special tokens.
  • Review model provider configurations for filtering.
References
References to Advisories, Solutions, and Tools

Here, you will find a curated list of external links that provide in-depth information, practical solutions, and valuable tools related to CVE-2026-61732.

URL Resource
https://github.com/BitterSecurity/Decepticon/commit/79ee2aaf22f4c36a5b1968f6ca3f8086b6e35b67
https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf
https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-61732 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-61732 weaknesses.

CAPEC-3: Using Leading 'Ghost' Character Sequences to Bypass Input Filters Using Leading 'Ghost' Character Sequences to Bypass Input Filters CAPEC-6: Argument Injection Argument Injection CAPEC-7: Blind SQL Injection Blind SQL Injection CAPEC-8: Buffer Overflow in an API Call Buffer Overflow in an API Call CAPEC-9: Buffer Overflow in Local Command-Line Utilities Buffer Overflow in Local Command-Line Utilities CAPEC-10: Buffer Overflow via Environment Variables Buffer Overflow via Environment Variables CAPEC-13: Subverting Environment Variable Values Subverting Environment Variable Values CAPEC-14: Client-side Injection-induced Buffer Overflow Client-side Injection-induced Buffer Overflow CAPEC-24: Filter Failure through Buffer Overflow Filter Failure through Buffer Overflow CAPEC-28: Fuzzing Fuzzing CAPEC-34: HTTP Response Splitting HTTP Response Splitting CAPEC-42: MIME Conversion MIME Conversion CAPEC-43: Exploiting Multiple Input Interpretation Layers Exploiting Multiple Input Interpretation Layers CAPEC-45: Buffer Overflow via Symbolic Links Buffer Overflow via Symbolic Links CAPEC-46: Overflow Variables and Tags Overflow Variables and Tags CAPEC-47: Buffer Overflow via Parameter Expansion Buffer Overflow via Parameter Expansion CAPEC-51: Poison Web Service Registry Poison Web Service Registry CAPEC-52: Embedding NULL Bytes Embedding NULL Bytes CAPEC-53: Postfix, Null Terminate, and Backslash Postfix, Null Terminate, and Backslash CAPEC-64: Using Slashes and URL Encoding Combined to Bypass Validation Logic Using Slashes and URL Encoding Combined to Bypass Validation Logic CAPEC-67: String Format Overflow in syslog() String Format Overflow in syslog() CAPEC-71: Using Unicode Encoding to Bypass Validation Logic Using Unicode Encoding to Bypass Validation Logic CAPEC-72: URL Encoding URL Encoding CAPEC-76: Manipulating Web Input to File System Calls Manipulating Web Input to File System Calls CAPEC-78: Using Escaped Slashes in Alternate Encoding Using Escaped Slashes in Alternate Encoding CAPEC-79: Using Slashes in Alternate Encoding Using Slashes in Alternate Encoding CAPEC-80: Using UTF-8 Encoding to Bypass Validation Logic Using UTF-8 Encoding to Bypass Validation Logic CAPEC-83: XPath Injection XPath Injection CAPEC-84: XQuery Injection XQuery Injection CAPEC-101: Server Side Include (SSI) Injection Server Side Include (SSI) Injection CAPEC-105: HTTP Request Splitting HTTP Request Splitting CAPEC-108: Command Line Execution through SQL Injection Command Line Execution through SQL Injection CAPEC-120: Double Encoding Double Encoding CAPEC-135: Format String Injection Format String Injection CAPEC-250: XML Injection XML Injection CAPEC-267: Leverage Alternate Encoding Leverage Alternate Encoding CAPEC-273: HTTP Response Smuggling HTTP Response Smuggling

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-61732 vulnerability anywhere in the article.

Results are limited to the first 20 news articles due to potential performance issues.

The following table lists the changes that have been made to the CVE-2026-61732 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0

    Sep. 24, 2026

    Action Type Old Value New Value
    Added Reference https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf
    Added SSVC {'id': 'CVE-2026-61732', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'yes'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-09-24T17:59:08.643777Z'}
  • New CVE Received by [email protected]

    Sep. 24, 2026

    Action Type Old Value New Value
    Added 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.
    Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
    Added CWE CWE-74
    Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/61xxx/CVE-2026-61732.json">CVE-2026-61732</a>
    Added Reference https://github.com/BitterSecurity/Decepticon/commit/79ee2aaf22f4c36a5b1968f6ca3f8086b6e35b67
    Added Reference https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.
CVSS
Vulnerability Scoring Details
Base CVSS Score: 10.0
Attack Vector
Attack Complexity
Privileges Required
User Interaction
Scope
Confidentiality Impact
Integrity Impact
Availability Impact