Operator-host command execution via unsanitized SSH output
Published Sep 14, 2026 · Updated Sep 14, 2026
Command injection in HackingBuddyGPT 0.5.0 and earlier allows remote attackers controlling an SSH target to execute commands on the operator host. ssh_run_command returns raw target output into conversation history, where the LLM treats it as instructions and local_shell passes generated commands to tmux send-keys without validation. Exploitation requires an operator to connect the tool to an attacker-controlled or compromised SSH target; resulting commands run with the operator's privileges outside a sandbox.
Summary
What happened
Command injection in HackingBuddyGPT 0.5.0 and earlier allows remote attackers controlling an SSH target to execute commands on the operator host. ssh_run_command returns raw target output into conversation history, where the LLM treats it as instructions and local_shell passes generated commands to tmux send-keys without validation. Exploitation requires an operator to connect the tool to an attacker-controlled or compromised SSH target; resulting commands run with the operator's privileges outside a sandbox.
The record
- CVE
- CVE-2026-90621
- Published
- Sep 14, 2026
- Updated
- Sep 14, 2026
- Vendor
- Interactive Programming & Analysis (TU Wien)
- Product
- HackingBuddyGPT
- Classifications
- T1059.004
- Attack vector
- network
- Privileges
- Unavailable
Timeline
How it unfolded
- Sep 14, 2026CVE publishedPublication date reported by the CVE source.
- Sep 14, 2026Record 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=0.1
- Affected versionversion=0.2
- Affected versionversion=0.3
- Affected versionversion=0.4
- Affected versionversion=0.5.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
No CVSS assessment is available in this record.
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
- Target-side prompt-injection proof of conceptproof of concept · unverified
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