CVE-2026-61732
Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context
Einstufung nach Quelle
Trivys eigenes Label ist CRITICAL. Kritisch laut GHSA.
Beschreibung
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.
Betroffene Pakete und behobene Versionen
| Quelle | Paket | Behoben in |
|---|---|---|
| pip::GitHub Security Advisory pip | decepticon, decepticon-core, decepticon-sdk | 1.1.17 |
Alle 3 Einträge aus 1 Quelle zeigen
| Quelle | Paket | Behoben in |
|---|---|---|
| pip::GitHub Security Advisory pip | decepticon | 1.1.17 |
| pip::GitHub Security Advisory pip | decepticon-core | 1.1.17 |
| pip::GitHub Security Advisory pip | decepticon-sdk | 1.1.17 |
Referenzen
- https://github.com/BitterSecurity/Decepticon/commit/79ee2aaf22f4c36a5b1968f6ca3f8086b6e35b67
- https://github.com/BitterSecurity/Decepticon/pull/715
- https://github.com/BitterSecurity/Decepticon/releases/tag/v1.1.17
- https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf
- https://github.com/PurpleAILAB/Decepticon
- https://nvd.nist.gov/vuln/detail/CVE-2026-61732