What’s Vulnerable › Vulnerabilities

CVE-2026-61732: Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context

• Severity: critical (CVSS 10.0 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 1.5% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-09-24 · updated 2026-09-30
• Weakness: CWE-74

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.

Affected products

• BitterSecurity Decepticon: before 1.1.17
• BitterSecurity decepticon-core: before 1.1.17
• BitterSecurity decepticon-sdk: before 1.1.17

References

• https://github.com/BitterSecurity/Decepticon/commit/79ee2aaf22f4c36a5b1968f6ca3f8086b6e35b67
• https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf
• https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf

Get alerted when CVE-2026-61732 or the next vulnerability affects your stack