CVE-2024-6331

Injection by Prompt Injection in stitionai/devika

CVSS 7.5 HIGHEPSS 0.5%CWE-74

Vexday Risk Score

21Low

SSVC decision (CISA)

Track

No exploitation signal → monitor

CVSS 7.5EPSS 0.5%KEV nãoPoC —Nuclei —Metasploit —Patch —

Lifecycle

04 Aug 2024Published on NVD

Recommendation: Monitor — no exploitation signal at the moment.

stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like `/etc/passwd`.

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Affected products

stitionai · stitionai/devika

Want to know if your infrastructure is exposed to this?

Talk to TrueHacking →

References

https://huntr.com/bounties/d5ac1051-22fa-42f0-8d82-73267482e60f