Hermes Agent是Nous Research开源的一款具备自我学习循环的AI代理工具。 Hermes Agent 2026.4.30及之前版本存在安全漏洞,该漏洞源于tools/memory_tool.py文件中_scan_memory_content函数问题,可能导致注入攻击。
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| NousResearch | hermes-agent | 2026.4.0 |
affected |
2026.4.1 |
affected | ||
2026.4.2 |
affected | ||
2026.4.3 |
affected | ||
2026.4.4 |
affected | ||
2026.4.5 |
affected | ||
2026.4.6 |
affected | ||
2026.4.7 |
affected | ||
| … +23 more rows | |||
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| NousResearch | hermes-agent | 2026.4.0 |
cpe:2.3:a:nousresearch:hermes-agent:*:*:*:*:*:*:*:*
|
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2026-10220 | 7.3 HIGH | NousResearch hermes-agent skills_tool.py skill_view injection |
| CVE-2026-10221 | 7.3 HIGH | NousResearch hermes-agent run_agent.py _compress_context injection |
| CVE-2026-10222 | 5.6 MEDIUM | NousResearch hermes-agent config.py _sanitize_env_lines injection |
| CVE-2026-10224 | 5.3 MEDIUM | NousResearch hermes-agent Webhook Endpoint feishu.py _handle_webhook_request resource cons |
No comments yet