Отправить #812216: NousResearch hermes-agent 2026.4.23 Injection (CWE-74)Информация

НазваниеNousResearch hermes-agent 2026.4.23 Injection (CWE-74)
Описание# Technical Details A multi-word prompt injection bypass exists in the skills threat detection logic in `agent/skills_guard.py` of hermes-agent. The application fails to consistently apply flexible whitespace and multi-word matching regex across all threat patterns (`THREAT_PATTERNS`), specifically leaving the "system prompt override" and "new policy" patterns vulnerable to bypass by injecting extraneous filler words. # Vulnerable Code File: agent/skills_guard.py Method: THREAT_PATTERNS definition Why: While some regex patterns were patched to accommodate multi-word inclusions via `(?:\w+\s+)*`, critical filters like `r'system\s+prompt\s+override'` and `r'new\s+policy'` remain rigid. Injecting words such as `system prompt temporary override` evades the matcher. # Reproduction 1. Create a malicious skill payload containing the phrase `system prompt temporary override`. 2. Submit the payload to the agent's `skills_guard.py` install process. 3. The regex fails to match the injected threat pattern, leading to the payload being accepted as a safe skill. 4. The system prompt is subsequently overridden implicitly without quarantine. # Impact - Evasion of "Critical" severity skill checks, allowing malicious skills to be installed into the workspace. - Unauthorized manipulation of the agent's execution logic by persistently hijacking future sessions to run arbitrary malicious actions or override policies without detection.
Источник⚠️ https://gist.github.com/YLChen-007/82a3539d6358842e69dfaef0a9fcf14a
Пользователь
 Eric-i (UID 97584)
Представление24.04.2026 14:43 (1 месяц назад)
Модерация23.05.2026 11:19 (29 days later)
Статуспринято
Запись VulDB365316 [NousResearch hermes-agent до 2026.4.23 Skills Guard Multi-Word Prompt agent/skills_guard.py THREAT_PATTERNS эскалация привилегий]
Баллы20

Want to stay up to date on a daily basis?

Enable the mail alert feature now!