Vulnerability 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.
CVSS Score
CRITICAL
Related Weaknesses (CWE)
References
- https://github.com/BitterSecurity/Decepticon/commit/79ee2aaf22f4c36a5b1968f6ca3f
- https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-
- https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-
FAQ
What is CVE-2026-61732?
CVE-2026-61732 is a vulnerability with a CVSS score of 10.0 (CRITICAL). 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 neutra...
How severe is CVE-2026-61732?
CVE-2026-61732 has been rated CRITICAL with a CVSS base score of 10.0/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-61732?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.