Remote Python execution via implicit tool approval
Published Jul 19, 2026 · Updated Jul 19, 2026
Code injection in RT-Claw unreleased main after 0.2.0 allows remote attackers to execute Python through Telegram-originated AI tool calls. The AI dispatch loops call claw_tool_invoke without an approval gate, and the Linux run_script backend writes attacker-influenced code to a temporary file and starts it with python3. Exploitation requires Telegram and run_script to be enabled and the model to return the tool call; code runs with the rtclaw process privileges.
Summary
What happened
Code injection in RT-Claw unreleased main after 0.2.0 allows remote attackers to execute Python through Telegram-originated AI tool calls. The AI dispatch loops call claw_tool_invoke without an approval gate, and the Linux run_script backend writes attacker-influenced code to a temporary file and starts it with python3. Exploitation requires Telegram and run_script to be enabled and the model to return the tool call; code runs with the rtclaw process privileges.
The record
- CVE
- CVE-2026-16204
- Published
- Jul 19, 2026
- Updated
- Jul 19, 2026
- Vendor
- Zevorn
- Product
- RT-Claw
- Classifications
- CWE-94, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 19, 2026CVE publishedPublication date reported by the CVE source.
- Jul 19, 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=0.2.0
What conditions does exploitation require?
What is affected?
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
- verification_test.py end-to-end harnessfunctional · 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