जमा करें #822021: NousResearch hermes-agent <= v2026.4.30 Injection (CWE-74)जानकारी

शीर्षकNousResearch hermes-agent <= v2026.4.30 Injection (CWE-74)
विवरण# Technical Details A Persistent Prompt Injection exists in the `_scan_memory_content` method in `tools/memory_tool.py` and `tools/mcp_tool.py` of hermes-agent. The application fails to correctly handle intervening words in its prompt injection regex patterns, allowing multi-word bypass payloads to be written to persistent memory. # Vulnerable Code File: tools/memory_tool.py Method: _scan_memory_content Why: The regex `(r'ignore\s+(previous|all|above|prior)\s+instructions', "prompt_injection")` expects exactly one separating keyword. Payloads with extra words bypass the scanner. # Reproduction 1. Send a crafted message with a multi-word payload (e.g., "ignore ALL prior instructions") via any external interface (API, Discord, Slack). 2. The LLM processes the request and calls the memory tool to save the content. 3. The scanner returns `None` (bypass) and the injection payload is written to `MEMORY.md`. 4. On the next session start, the payload is persistently injected into the agent's system prompt. # Impact - Permanently alter the agent's instructions, persona, or goals for all future sessions. - Establish a persistent backdoor that survives restarts and overrides safety constraints.
स्रोत⚠️ https://gist.github.com/YLChen-007/a1fb77ad2488c545a35d0f66356ea7b4
उपयोगकर्ता
 Eric-j (UID 98073)
सबमिशन07/05/2026 03:41 PM (29 दिन पहले)
संयम31/05/2026 09:51 AM (24 days later)
स्थितिस्वीकृत
VulDB प्रविष्टि367502 [NousResearch hermes-agent तक 2026.4.30 tools/memory_tool.py _scan_memory_content अधिकार वृद्धि]
अंक20

Want to know what is going to be exploited?

We predict KEV entries!