VYPR
Unrated severityNVD Advisory· Published Aug 4, 2024· Updated Aug 30, 2024

Injection by Prompt Injection in stitionai/devika

CVE-2024-6331

Description

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.

Affected products

2
  • Stitionai/Devikallm-fuzzy
    Range: <= commit cdfb782b0e634b773b10963c8034dc9207ba1f9f
  • stitionai/stitionai/devikav5
    Range: unspecified

Patches

0

No patches discovered yet.

Vulnerability mechanics

AI mechanics synthesis has not run for this CVE yet.

References

1

News mentions

0

No linked articles in our index yet.