CVE-2024-10950
In binary-husky/gpt_academic version <= 3.83, the plugin `CodeInterpreter` is vulnerable to code injection caused by prompt injection.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (1.48%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
In binary-husky/gpt_academic version <= 3.83, the plugin `CodeInterpreter` is vulnerable to code injection caused by prompt injection. The root cause is the execution of user-provided prompts that generate untrusted code without a sandbox, allowing the execution of parts of the LLM-generated code. This vulnerability can be exploited by an attacker to achieve remote code execution (RCE) on the application backend server, potentially gaining full control of the server.
- CVSS 3.0
- 8.8 HIGHCVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 1.48% probability · 72th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-94
- Affected
- binary-husky/gpt academic
- Source
- security@huntr.dev
References
- https://huntr.com/bounties/9abb1617-0c1d-42c7-a647-d9d2b39c6866Exploit, Third Party Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.