提出 #822019: NousResearch hermes-agent <= 0.12.0 Injection (CWE-74)情報

タイトルNousResearch hermes-agent <= 0.12.0 Injection (CWE-74)
説明# Technical Details A Prompt Injection vulnerability exists in the `_compress_context` method in `run_agent.py` and `TodoStore.format_for_injection()` in `tools/todo_tool.py` of hermes-agent. The application fails to sanitize or escape todo item contents before appending them directly into the compressed message array as an authoritative `{"role": "user"}` message. # Vulnerable Code File: run_agent.py and tools/todo_tool.py Method: _compress_context and TodoStore.format_for_injection Why: Raw todo item content is appended directly as an authoritative user message at the end of the context during compression, allowing attacker payloads to override prior system instructions. # Reproduction 1. Interact with the agent to create a malicious todo item containing an injection payload (e.g., via the `/v1/chat/completions` API). 2. Continue the conversation until context compression is triggered. 3. The injected payload becomes the last user message in the context, successfully hijacking the agent's behavior. # Impact - Override system instructions and safety directives. - Exfiltrate sensitive data such as environment variables or API keys, and abuse tools to execute shell commands.
ソース⚠️ https://gist.github.com/YLChen-007/d343fcfe2c009cd45f56dc475fd5ac03
ユーザー
 Eric-j (UID 98073)
送信2026年05月07日 15:38 (1 月 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367500 [NousResearch hermes-agent 迄 0.12.0 run_agent.py _compress_context 特権昇格]
ポイント20

Want to stay up to date on a daily basis?

Enable the mail alert feature now!