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

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

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

EPSS

• CVE-2026-61732: 1.47% estimated exploitation activity in the next 30 days; percentile 73.79 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary Decepticon wraps 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. The vast majority of open-source and self-deployed model providers do not filter special-token literals. vLLM explicitly declined to fix this issue on 2026-04-21, closing it as "out of…

Published by the source

24 Sep 2026, 19:17 UTC

Last modified by the source

1 Oct 2026, 17:55 UTC

Source last checked

26 Oct 2026, 13:54 UTC

1. Revision 3 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-g5f9-3xfg-p9mf

2. Revision 2 · amended · 24 Oct 2026

   Amended from osv record GHSA-g5f9-3xfg-p9mf

3. Revision 1 · created · 23 Oct 2026

   Published from ghsa record GHSA-g5f9-3xfg-p9mf

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-61732

Advisory: Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context
IDs: CVE-2026-61732, GHSA-g5f9-3xfg-p9mf
Record: https://patchnext.com/advisories/cve-2026-61732 (revision 3, source checked 26 Oct 2026, 13:54 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Critical (CVSS 10.0)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: decepticon-core 1.1.17; decepticon-sdk 1.1.17; decepticon 1.1.17. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI decepticon-core: affected <= 1.1.16; fixed in 1.1.17
- PyPI decepticon-sdk: affected <= 1.1.16; fixed in 1.1.17
- PyPI decepticon: affected <= 1.1.16; fixed in 1.1.17

## Suggested inspection (read-only)
- `python -m pip show decepticon-core`: prints the installed version. Run with the environment that serves production active.
- `python -m pip show decepticon-sdk`: prints the installed version. Run with the environment that serves production active.
- `python -m pip show decepticon`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on decepticon-core, decepticon-sdk, decepticon.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://github.com/advisories/GHSA-g5f9-3xfg-p9mf (GitHub-reviewed advisory GHSA-g5f9-3xfg-p9mf lists affected ranges: PyPI decepticon-core >=0 =0 =0 <=1.1.16)
- Verified: https://osv.dev/vulnerability/GHSA-g5f9-3xfg-p9mf (OSV record GHSA-g5f9-3xfg-p9mf lists affected ranges: PyPI decepticon-core >=0 =0 =0 <1.1.17 (fixed))

Commands are suggestions: review each one before running it.