Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-g5f9-3xfg-p9mf

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

CVSS 10.0 CriticalCriticalEPSS 0.015 · 73rd percentile

Critical, because:

  • CVSS score 10.0: 9.0 or more.

How we decide what’s critical

Published by the GitHub Advisory Database at 24 Sept 2026, 19:17 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
decepticon-corePyPI<1.1.171.1.17
decepticonPyPI<1.1.171.1.17
decepticon-sdkPyPI<1.1.171.1.17
Identifiers
GHSA-g5f9-3xfg-p9mf · CVE-2026-61732 · PYSEC-2026-4032 · PYSEC-2026-4033 · PYSEC-2026-4034
Weakness (CWE)
CWE-74
Tags
Published
24 Sept 2026
Updated
1 Oct 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

Decepticon versions before 1.1.17 (packages decepticon-core, decepticon, and decepticon-sdk) pass web crawl results into LLM context without neutralizing ChatML special-token literals. An attacker who controls a target web page can plant these literals so the model treats forged operator turns as authoritative, which can lead to arbitrary command execution in the Kali Linux sandbox. Upgrade to version 1.1.17 or later.

Written 1 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
10.0 Critical 3.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.015, the 73rd percentile, on 10 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:09 UTC First seen by agentprime
  2. 31 Oct 2026, 14:09 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.