CVE-2026-61732

CRITICALPre-NVD 10.010.0—
EchelonGraph scoreMEDIUM confidence

This critical-severity CVE scores 10.0 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 1.2% (67th percentile of EPSS-scored CVEs). GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).

Triggered by: NVD CVSS baseline
Sources: epss, secondary
10.0EG
EchelonGraph verdictPlan a fixSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 1.2%CVSS: 10.0Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

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.

CVSS v3
10.0
EG Score
10.0CRITICALmedium confidence
EG Risk
50
EG Risk 50/100CISA SSVC

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed
Severity100% × 45%
Exploitation1% × 40%
Automatability30% × 15%
CISA SSVC: Track at low or medium mission impact; Track* or Attend at high (mission-essential systems).
Action: A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.
EPSS PROB
1.2%
EPSS %ILE
67th
KEV
Not listed

CISA SSVCTrack at low or medium mission impact; Track* or Attend at high (mission-essential systems).

A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.

Exploitation none (no KEV listing, exploit record or EPSS ≥ 50%) · Automatable unknown (not published for this CVE) · Technical impact total (CVSS ≥ 9.0). Mission impact is CISA's Mission & Well-being decision point, and only you can judge it: high means the affected system is essential to your organisation's mission, or its compromise could cause irreversible harm to people. CISA's decision table

Published

September 24, 2026

Last Modified

September 30, 2026

Advisory Details (2)

Auto-updated Sep 30, 2026
Patch available. Sources: github_commit, github.
github Patch Available

Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context · Advisory · BitterSecurity/Decepticon · GitHub

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

commit 79ee2aaf22f4 (BitterSecurity/Decepticon)

Fix landed in BitterSecurity/Decepticon commit 79ee2aaf22f4 — awaiting tagged release

https://github.com/BitterSecurity/Decepticon/commit/79ee2aaf22f4c36a5b1968f6ca3f8086b6e35b67

Vendor Advisories for CVE-2026-61732(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Affected Packages

(3 across 1 ecosystem)
PyPI(3)
PackageVulnerable rangeFix by version rangeDependents
decepticon1.1.0 ... 1.1.9 (17 versions)
  • every version up to 1.1.17: fixed in 1.1.17
—
decepticon-core1.1.10 ... 1.1.9 (15 versions)
  • every version up to 1.1.17: fixed in 1.1.17
—
decepticon-sdk1.1.10 ... 1.1.9 (15 versions)
  • every version up to 1.1.17: fixed in 1.1.17
—

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 14× in last 7d / 21× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-10-05 03:34 UTCEG score recompute
  2. 2026-10-04 23:22 UTCEPSS rescore
  3. 2026-10-03 16:15 UTCEG score recompute
  4. 2026-10-03 14:26 UTCEPSS rescore
  5. 2026-10-02 18:12 UTCEG score recompute
  6. 2026-10-02 17:56 UTCEPSS rescore
  7. 2026-10-01 19:59 UTCEG score recompute
  8. 2026-10-01 19:50 UTCEPSS rescore
  9. 2026-09-30 17:33 UTCEG score recompute
  10. 2026-09-30 15:03 UTCEPSS rescore
  11. 2026-09-29 19:32 UTCEG score recompute
  12. 2026-09-29 01:49 UTCEG score recompute
  13. 2026-09-28 17:02 UTCEG score recompute
  14. 2026-09-28 13:51 UTCEPSS rescore
  15. 2026-09-27 14:26 UTCEG score recompute
  16. 2026-09-26 16:19 UTCEG score recompute
  17. 2026-09-26 15:59 UTCEPSS rescore
  18. 2026-09-26 03:02 UTCEG score recompute
  19. 2026-09-24 18:35 UTCEG score recompute
  20. 2026-09-24 17:47 UTCEG score recompute
  21. 2026-09-24 17:46 UTCMITRE cvelistV5first tracked

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-61732?
CVE-2026-61732 is a critical vulnerability published on September 24, 2026. 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…
When was CVE-2026-61732 disclosed?
CVE-2026-61732 was first published on September 24, 2026, with the most recent update on September 30, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-61732 actively exploited?
CVE-2026-61732 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 1.2% probability of exploitation in the next 30 days (67th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-61732?
CVE-2026-61732 has a CVSS base score of 10.0 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-61732?
A fix for CVE-2026-61732 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-61732 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-61732

Explore →

Is Your Infrastructure Affected by CVE-2026-61732?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Book a Demo →Browse All CVEs