Log in Start free

Vulnerability · Published Aug 4, 2024 · Assigned by @huntr_ai

CVE-2024-6331Injection by Prompt Injection in stitionai/devika

High 7.5

In plain English

A high-severity injection in stitionai/devika from stitionai. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 43% of all known vulnerabilities).

Severity (CVSS 3.1)7.5High
Exploit odds (30 days)0.5%top 57.2% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official 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 (as reported)

VendorProductVersions
stitionai stitionai/devika unspecified – through latest

Weakness: CWE-74 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

References