Console message spoofing via unfiltered ANSI escapes
Published Jul 13, 2023 · Updated Oct 22, 2024
Improper output neutralization in AutoGPT before 0.4.3 allows remote attackers to spoof console messages through malicious web content. The print_assistant_thoughts function passes JSON-decoded text, reasoning, plan, criticism, and speech fields to color-capable console handlers without stripping ESC bytes. Exploitation requires a browsed attacker-controlled resource, model reproduction of the encoded sequence, and operator review; it can falsify approval cues but does not itself execute commands.
Summary
What happened
Improper output neutralization in AutoGPT before 0.4.3 allows remote attackers to spoof console messages through malicious web content. The print_assistant_thoughts function passes JSON-decoded text, reasoning, plan, criticism, and speech fields to color-capable console handlers without stripping ESC bytes. Exploitation requires a browsed attacker-controlled resource, model reproduction of the encoded sequence, and operator review; it can falsify approval cues but does not itself execute commands.
The record
- CVE
- CVE-2023-37275
- Published
- Jul 13, 2023
- Updated
- Oct 22, 2024
- Vendor
- Significant Gravitas
- Product
- AutoGPT
- Classifications
- CWE-117, T1036
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 13, 2023CVE publishedPublication date reported by the CVE source.
- Oct 22, 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=< 0.4.3
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.
Public exploit references
- ANSI console-injection demonstrationproof 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