Remote code execution via safe_eval restriction bypass
Published Apr 10, 2024 · Updated Aug 1, 2024
Code injection in Run Llama LlamaIndex before 0.10.24 allows remote attackers to execute arbitrary code through crafted LLM prompts. The exec_utils safe_eval function insufficiently validates generated expressions, allowing crafted input to bypass its method restrictions before Python evaluation. Exposure requires a host application to pass attacker-influenced LLM output into the affected evaluator, after which code runs with the host process's privileges.
Summary
What happened
Code injection in Run Llama LlamaIndex before 0.10.24 allows remote attackers to execute arbitrary code through crafted LLM prompts. The exec_utils safe_eval function insufficiently validates generated expressions, allowing crafted input to bypass its method restrictions before Python evaluation. Exposure requires a host application to pass attacker-influenced LLM output into the affected evaluator, after which code runs with the host process's privileges.
The record
- CVE
- CVE-2024-3098
- Published
- Apr 10, 2024
- Updated
- Aug 1, 2024
- Vendor
- Run Llama
- Product
- LlamaIndex
- Classifications
- CWE-94, T1059
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Apr 10, 2024CVE publishedPublication date reported by the CVE source.
- Aug 1, 2024Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <0.10.24
- Affected versionversion=unspecified <0.10.24
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Huntr safe_eval restriction-bypass proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo