Skip to main content
Public proof of conceptFix available

CVE-2026-61732

A public proof of concept exists; no exploitation attested.

  • Published2026-09-24
  • Fixed in1.1.17
  • WeaknessCWE-74

Am I affected?

With a domain, we read the version its public headers and pages expose. A distribution build can carry the fix under an older number.

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.

Timeline

dates in UTC
  1. 2026-09-2418:17CVE publishedNVD

Versions per branch

OSV
decepticon
BranchAffectedFixed in
1.1< 1.1.171.1.17
decepticon-core
BranchAffectedFixed in
1.1< 1.1.171.1.17
decepticon-sdk
BranchAffectedFixed in
1.1< 1.1.171.1.17

as publishedRanges as NVD and OSV publish them; a distribution’s build can be fixed under an older number.

Products declared by the CNA3 products

As GitHub_M, the CNA that assigned this CVE, declared them in the CVE record; versions as written.

  • BitterSecurity Decepticon
    Affected
    • = < 1.1.17no fix stated
  • BitterSecurity decepticon-core
    Affected
    • = < 1.1.17no fix stated
  • BitterSecurity decepticon-sdk
    Affected
    • = < 1.1.17no fix stated

Source: the CNA record (CVE Program), © The MITRE Corporation,CVE Terms of UseCVE recordupdated 2026-09-24

Fix

  1. Update decepticon to 1.1.17

Detection

read 2026-11-01 01:02 UTC
Nuclei template
none so far
ProjectDiscovery
Exploit-DB
no entry
Exploit-DB
Proof of concept
Metasploit modules
none listed
Metasploit Framework

Sources

Identifiers

Technical details

CVSS v3 Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Published
2026-09-24
Last Modified
2026-09-30
NVD status
Deferred
GitHub Advisory
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.

Is CVE-2026-61732 actively exploited?

A proof-of-concept exploit exists for CVE-2026-61732, but active exploitation has not been confirmed at this time.

What is the CVSS score for CVE-2026-61732?

CVE-2026-61732 has a CVSS v3 base score of 10 (CRITICAL severity), with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H.

Running decepticon? Hear about its next vulnerability

Surveillance reads the versions in your stack — a domain, a lockfile or a list — checks each CVE against the ranges its sources publish, and alerts you when one you run is exploited or enters CISA KEV. A version it cannot read stays « version not verified ».

No credit card required · No monthly cap on website lookups · 250 API requests/month

Sources for this record