---
title: "CVE-2026-61732: Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context"
url: https://erroneo.us/security/cve/CVE-2026-61732/
description: "CVE-2026-61732 (decepticon-core (PyPI)): Decepticon is an autonomous hacking agent for red teams. Versions prior to 1.1.17 wrap web crawl results — the…"
type: vulnerability-record
section: "Security Digest"
date_published: 2026-09-24
date_modified: 2026-09-24
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2026-61732"
kev: false
cvss: 10
epss: 0.01221
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2026-61732: Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context

**Signal:** Critical and remotely reachable. No known exploitation yet, but it is network-reachable without credentials. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 1.2% , percentile 68: FIRST’s model estimates a 1.2% chance of exploitation activity in the next 30 days, higher than 68% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes decepticon-core (PyPI) <= 1.1.16, fixed in 1.1.17 ; decepticon (PyPI) <= 1.1.16, fixed in 1.1.17 ; decepticon-sdk (PyPI) <= 1.1.16, fixed in 1.1.17 . Check your lockfile, including transitive dependencies.

## What it is

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.

## Affected packages

- PyPI `decepticon-core` <= 1.1.16 → fixed: 1.1.17
- PyPI `decepticon` <= 1.1.16 → fixed: 1.1.17
- PyPI `decepticon-sdk` <= 1.1.16 → fixed: 1.1.17

## Affected products (CVE record)

- BitterSecurity Decepticon: < 1.1.17
- BitterSecurity decepticon-core: < 1.1.17
- BitterSecurity decepticon-sdk: < 1.1.17

## Severity

- GitHub_M CVSS 3.1: 10 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`
- GitHub CVSS 3.1: 10.0 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable yes , technical impact total .
- FIRST EPSS (model of 2026-10-21): 1.22% probability of exploitation activity in the next 30 days; percentile 68.

## Sources

- [GitHub Advisory GHSA-g5f9-3xfg-p9mf](https://github.com/advisories/GHSA-g5f9-3xfg-p9mf)
- [CVE.org record CVE-2026-61732](https://www.cve.org/CVERecord?id=CVE-2026-61732)
- [NVD entry CVE-2026-61732](https://nvd.nist.gov/vuln/detail/CVE-2026-61732)
- [github.com](https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf)
- [github.com](https://github.com/BitterSecurity/Decepticon/commit/79ee2aaf22f4c36a5b1968f6ca3f8086b6e35b67)
- [github.com](https://github.com/BitterSecurity/Decepticon/pull/715)
- [github.com](https://github.com/BitterSecurity/Decepticon/releases/tag/v1.1.17)

---
Source page: https://erroneo.us/security/cve/CVE-2026-61732/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt