提出 #822021: NousResearch hermes-agent <= v2026.4.30 Injection (CWE-74)情報

タイトルNousResearch hermes-agent <= v2026.4.30 Injection (CWE-74)
説明# 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.
ソース⚠️ https://gist.github.com/YLChen-007/a1fb77ad2488c545a35d0f66356ea7b4
ユーザー
 Eric-j (UID 98073)
送信2026年05月07日 15:41 (28 日 ago)
モデレーション2026年05月31日 09:51 (24 days later)
ステータス承諾済み
VulDBエントリ367502 [NousResearch hermes-agent 迄 2026.4.30 tools/memory_tool.py _scan_memory_content 特権昇格]
ポイント20

Do you need the next level of professionalism?

Upgrade your account now!