What happened
In controlled testing, Decepticon crawled attacker-controlled web content, composed preserved ChatML role tokens into model context, and executed a shell command selected by the attacker.
2026-09-24
HighPrimaryCVE-2026-61732 let ChatML tokens in crawled web content forge model roles and make a Decepticon red-team agent execute an attacker-chosen command.
What happened
In controlled testing, Decepticon crawled attacker-controlled web content, composed preserved ChatML role tokens into model context, and executed a shell command selected by the attacker.
Why it matters
The demonstration created an attacker-chosen marker file inside the Decepticon Kali sandbox. The vulnerable path applied across the agent roster when used with model backends that preserved special-token IDs.
Missing authorization check
A policy decision independent of model context before command execution, bound to the target, command, environment, and authorized engagement.
Would PP block it?
Credential use, target-system mutation, data export, repository changes, and infrastructure operations could require receipts evaluated outside the compromised agent and model context. The forged role token would not itself satisfy that authorization.
Incident analysis
2026-09-24
The Decepticon security advisory publishes the controlled role-forgery reproduction as GHSA-g5f9-3xfg-p9mf and CVE-2026-61732.
2026-09-24
Decepticon 1.1.17 is identified as the first patched release.
Authorization boundary
This incident is categorized as Tool execution / MCP. The relevant Permission Protocol gate is Runtime Gate. The read is conditional: the block only applies where the real action boundary is routed through a gate.
Permission Protocol cannot sanitize ChatML context or contain commands inside Decepticon's sandbox, but an external Runtime Gate can deny protected downstream actions that lack separately authenticated authority.
Related incidents and controls
Agentjacking: Attackers inject malicious instructions into fake Sentry errors via public DSN, hijacking Claude Code, Cursor, and Codex with 85% success rate across 2,388 organizations
Trend Micro: Poisoned mcp/postgres Docker Image Pulled 100K+ Times: Return-to-Tool Attack Causes AI Agent to Exfiltrate Production Tokens via Approved Tools
Start small
This incident maps to Runtime Gate. Start with the boundary that controls the actual action, then require a signed receipt before execution.