CVE-2026-61732: Injection (CVSS 10)

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.

Is your site exposed to CVE-2026-61732?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

10.0

CRITICAL

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

EPSS — Exploit Prediction

0.0122

Probability of exploitation

0.68%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-74 CWE-74

References

Other References

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

Frequently Asked Questions

What is CVE-2026-61732? +

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. It has a CVSS v3.1 base score of 10.0 (CRITICAL).

How severe is CVE-2026-61732? +

CVE-2026-61732 has a CVSS v3.1 score of 10.0 out of 10, rated CRITICAL. This is a critical vulnerability that should be patched immediately. The EPSS score is 0.0122, placing it in the 1th percentile for exploitation probability.

How do I check if I'm vulnerable to CVE-2026-61732? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2026-41237

Froxlor is open source server administration software. In version 2.3.6 and earlier, the LOC record regex uses `\s+` which matches …

CVE-2024-53263

Git LFS is a Git extension for versioning large files. When Git LFS requests credentials from Git for a remote …

CVE-2025-27107

Integrated Scripting is a tool for creating scripts for handling complex operations in Integrated Dynamics. Minecraft users who use Integrated …

CVE-2025-32699

Vulnerability in Wikimedia Foundation MediaWiki, Wikimedia Foundation Parsoid.This issue affects MediaWiki: before 1.39.12, 1.42.6, 1.43.1; Parsoid: before 0.16.5, 0.19.2, 0.20.2.

CVE-2025-40710

Host Header Injection (HHI) vulnerability in the Hotspot Shield VPN client, which can induce unexpected behaviour when accessing third-party web …

CVE-2025-6785

Securing externally available CAN wires can easily allow physical access to the CAN bus, allowing possible injection of specially formed …

CVE-2026-61732