Prohibited command execution via unnormalized paths
Published Sep 11, 2024 · Updated Sep 11, 2024
OS command injection in Significant Gravitas AutoGPT 0.5.1 allows remote attackers to execute denylisted commands through altered paths. The CodeExecutorComponent compares command paths against shell_denylist entries without canonicalizing redundant segments, so /bin/./whoami evades /bin/whoami. The bypass requires shell execution and denylist mode to be enabled and a workflow to supply a command; it defeats the configured restriction but does not itself create shell reachability.
Summary
What happened
OS command injection in Significant Gravitas AutoGPT 0.5.1 allows remote attackers to execute denylisted commands through altered paths. The CodeExecutorComponent compares command paths against shell_denylist entries without canonicalizing redundant segments, so /bin/./whoami evades /bin/whoami. The bypass requires shell execution and denylist mode to be enabled and a workflow to supply a command; it defeats the configured restriction but does not itself create shell reachability.
The record
- CVE
- CVE-2024-6091
- Published
- Sep 11, 2024
- Updated
- Sep 11, 2024
- Vendor
- Significant Gravitas
- Product
- AutoGPT
- Classifications
- CWE-78, T1059.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 11, 2024CVE publishedPublication date reported by the CVE source.
- Sep 11, 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 <0.5.1
- Affected versionversion=unspecified <0.5.1
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 shell denylist 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