Decepticon

Decepticon — Agente Autónomo de Red Team "¿Otro hacker de IA? Déjanos adivinar — ejecuta nmap y escribe un informe." ☁️ ¿No quieres autoalojarlo? Decepticon está disponible en la nube. Olvídate de la configuración de Docker — ejecuta compromisos autónomos de red team directamente desde tu...

Decepticon v1.2.2

Decepticon — Autonomous Red Team Agent "Another AI hacker? Let us guess — it runs nmap and writes a report." ☁️ Don't want to self-host? Decepticon is live in the cloud. Skip the Docker setup — run autonomous red-team engagements right from your browser. Install Prerequisites : Docker and Docker...

cve-2026-61732-lab

CVE-2026-61732 — Decepticon ChatML role-boundary forgery lab A self-contained, disposable lab that reproduces GHSA-g5f9-3xfg-p9mf / CVE-2026-61732: Decepticon , an autonomous red-team agent, wrapped web-crawl output into LLM messages without neutralizing ChatML special-token literals. On a...

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

SummaryDecepticon wraps 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...

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

SummaryDecepticon wraps 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...

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

SummaryDecepticon wraps 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...

Exploit for CVE-2026-61732

CVE-2026-61732 — Decepticon ChatML role-boundary forgery lab...

GHSA-G5F9-3XFG-P9MF Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context

Summary Decepticon wraps 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...

Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

Overview decepticon is an AI-powered autonomous red team testing framework Affected versions of this package are vulnerable to Improper Neutralization of Special Elements in Output Used by a Downstream Component 'Injection' via UntrustedOutputMiddleware.formatenvelope and...

Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

Overview decepticon-sdk is a Decepticon plugin author SDK: protocols, fixtures, scaffolding Affected versions of this package are vulnerable to Improper Neutralization of Special Elements in Output Used by a Downstream Component 'Injection' via UntrustedOutputMiddleware.formatenvelope and...

Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

Overview decepticon-core is a Decepticon contract layer: pure types, protocols, plugin contracts, registry primitives Affected versions of this package are vulnerable to Improper Neutralization of Special Elements in Output Used by a Downstream Component 'Injection' via...

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

Summary Decepticon wraps 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...

CVE-2026-61732

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...

EUVD-2026-86329

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...

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

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...

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

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...

CVE-2026-61732

Versions prior to 1.1.17 of Decepticon , an autonomous hacking agent, are vulnerable to a role-boundary forgery because they fail to neutralize ChatML special-token literals when wrapping web crawl results into LLM messages. When using the BYOK deployment model with common providers (such as vLLM...

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

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...

PT-2026-98193

Name of the Vulnerable Software and Affected Versions Decepticon versions prior to 1.1.17 Description Decepticon fails to neutralize ChatML special-token literals when wrapping web crawl results and other tool outputs into LLM messages. In Bring Your Own Key BYOK deployments using OpenAI-compatib...

CVE-2026-61732: Improper Neutralization of Special Elements in Output Used by a Downstream Component

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...