Vulnerability · Published Aug 6, 2025 · Assigned by VulDB
CVE-2025-8667SkyworkAI DeepResearchAgent tools.py from_mcp os command injection
Medium 6.3
In plain English
A medium-severity OS command injection in DeepResearchAgent from SkyworkAI. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 1.5% (higher than 74% of all known vulnerabilities).
Official description
A vulnerability, which was classified as critical, was found in SkyworkAI DeepResearchAgent up to 08eb7f8eb9505d0094d75bb97ff7dacc3fa3bbf2. Affected is the function from_code/from_dict/from_mcp of the file src/tools/tools.py. The manipulation leads to os command injection. It is possible to launch the attack remotely. The exploit has been disclosed to the public and may be used. Continious delivery with rolling releases is used by this product. Therefore, no version details of affected nor updated releases are available. The vendor was contacted early about this disclosure but did not respond in any way.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| SkyworkAI | DeepResearchAgent | 08eb7f8eb9505d0094d75bb97ff7dacc3fa3bbf2 |
Weakness: CWE-78, CWE-77 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R
References
- VDB-319026 | SkyworkAI DeepResearchAgent tools.py from_mcp os command injection vdb-entry, technical-description
- VDB-319026 | CTI Indicators (IOB, IOC, TTP, IOA) signature, permissions-required
- Submit #621324 | SkyworkAI DeepResearchAgent main OS Command Injection third-party-advisory
- https://github.com/bayuncao-bit/vul-36 broken-link
- https://github.com/bayuncao-bit/vul-36#proof-of-concept broken-link, exploit