Answer in brief
CVE-2026-61732 records a Critical severity (CVSS 10.0) vulnerability in Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context. The current sources do not mark it as known exploited. The current feed maps BitterSecurity/Decepticon (generic), BitterSecurity/decepticon-core (generic), BitterSecurity/decepticon-sdk (generic), decepticon (pip) and additional mapped packages. Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 10.0. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps BitterSecurity/Decepticon (generic), BitterSecurity/decepticon-core (generic), BitterSecurity/decepticon-sdk (generic), decepticon (pip) and additional mapped packages. Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| BitterSecurity/Decepticongeneric | <1.1.17 | 1.1.17 |
| BitterSecurity/decepticon-coregeneric | <1.1.17 | 1.1.17 |
| BitterSecurity/decepticon-sdkgeneric | <1.1.17 | 1.1.17 |
| decepticonpip | <=1.1.16 | 1.1.17 |
| decepticon-corepip | <=1.1.16 | 1.1.17 |
| decepticon-sdkpip | <=1.1.16 | 1.1.17 |
| decepticonpypi | >=0 <1.1.17 | 1.1.17 |
| decepticon-corepypi | >=0 <1.1.17 | 1.1.17 |
| decepticon-sdkpypi | >=0 <1.1.17 | 1.1.17 |
Published upstream
Sep 24, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Sep 24, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Sep 25, 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 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.
Quoted source text, attributed separately from HOL analysis.