CVE-2026-61732Critical· 10.0▾ AbyssalPoC availableDecepticon 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.…
▾ Abyssal zone — Critical with a public exploit or in-the-wild use
impact 55 · likelihood 0 · exploitation 12
A public proof-of-concept already exists for this vulnerability — see Exploit availability below.
Stakeholder-Specific Vulnerability Categorization from CISA's ADP record at CVE.org: whether exploitation is observed, whether an attack can be automated, and how much of the system is at stake.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
Exploit / PoC code exists
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.
Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Affected packages:
decepticon-core <= 1.1.16decepticon <= 1.1.16decepticon-sdk <= 1.1.16Patched in:
decepticon-core 1.1.17decepticon 1.1.17decepticon-sdk 1.1.17Field changes observed since this record was first indexed.
Connected by shared product, vendor, weakness, or advisory.
CVE-2022-27924High· 7.5Zimbra Collaboration (aka ZCS) 8.8.15 and 9.0 allows an unauthenticated attacker to inject arbitrary memcache commands into a targeted instance
CVE-2023-4548Medium· 6.3A vulnerability has been found in SPA-Cart eCommerce CMS 1.9.0.3
CVE-2026-19857Medium· 4.8The Formidable Forms WordPress plugin before 6.35 does not prevent a request-derived value from reaching the WordPress shortcode parser when it substitutes a supported token into a form's custom HTML, allowing unauthenticated visitors to…
CVE-2025-9236Medium· 6.3A vulnerability has been found in Portabilis i-Educar up to 2.10
CVE-2025-9606Medium· 6.3A vulnerability was detected in Portabilis i-Educar up to 2.10
CVE-2025-9531Medium· 6.3A vulnerability was detected in Portabilis i-Educar up to 2.10