Skip to content
Fencer Vulns
critical 10.0

CVE-2026-61732 json

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

published 2026-09-24 45 d ago modified 2026-10-01 38 d ago also GHSA-g5f9-3xfg-p9mf , PYSEC-2026-4032 , PYSEC-2026-4033 , PYSEC-2026-4034 , EUVD-2026-86329

cvss
10.0
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
1.5%
EPSS 1.5% chance of exploitation in 30 days, percentile 73%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi decepticon-core 1.1.17
  • pypi decepticon 1.1.17
  • pypi decepticon-sdk 1.1.17

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
total
Assessed
45 d ago

Exploit prediction

1.47% chance of exploitation in the next 30 days, higher than 73% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 10.0 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
OSV 3.1 10.0 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
GitHub 3.1 10.0 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi decepticon-core
<1.1.17
1.1.17
pypi decepticon
<1.1.17
1.1.17
pypi decepticon-sdk
<1.1.17
1.1.17

Affected products

  • BitterSecurity Decepticon
  • BitterSecurity decepticon-core
  • BitterSecurity decepticon-sdk

Classification

Weakness
  • CWE-74 Improper Neutralization of Special Elements in Output Used by a Downstream Component

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.