Back to feed
41Track*

Prompt Injection leading to Arbitrary Code Execution in run-llama/llama_index

run-llama/llama_index · CVE-2024-3098 GHSA-WVPX-G427-Q9WC
0 news outlets0 CERTs and agencies0 research labs

Assessment: Track*

SSVC decision points: exploitation poc, automatable yes, technical impact total, deployment low.

What is it?

A vulnerability was identified in the `exec_utils` class of the `llama_index` package, specifically within the `safe_eval` function, allowing for prompt injection leading to arbitrary code execution. This issue arises due to insufficient validation of input, which can be exploited to bypass method restrictions and execute unauthorized code. The vulnerability is a bypass of the previously addressed CVE-2023-39662, demonstrated through a proof of concept that creates a file on the system by exploiting the flaw.

Evidence

No coverage recorded yet.

Exploitation

  • Exploit code published (not verified by us)
  • Exploited in the wild (confirmed by a source)
  • Listed as known exploited (CISA KEV)
CVSS
9.8
EPSS
–
First seen
10 Apr 2024
Status
corroborated

All run-llama vulnerabilities