# CVE-2026-16204: zevorn rt-claw code injection in Telegram-to-AI Tool Execution Flow

Source: https://junglewise.ai/threats/cve-2026-16204-zevorn-rt-claw-code-injection-in-telegram-to-ai-tool-execution  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-07-19. Updated: 2026-07-19  
License: CC BY 4.0 with a link back

CVE-2026-16204 · Severity: medium · CVSS 6.3 · Published 2026-07-19

zevorn rt-claw is an AI assistant framework that integrates Telegram with AI models. A security flaw allows remote Telegram users to execute arbitrary Python code on the host system without any user approval. This could lead to full system compromise, data theft, or unauthorized access to the host environment where the assistant is running.

Technologies: [Zevorn Rt-Claw](https://junglewise.ai/threats/technologies/rt-claw). Vendors: [Zevorn](https://junglewise.ai/threats/vendors/zevorn).

## Quick answers

**Is CVE-2026-16204 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-16204 being exploited in the wild.

**How severe is CVE-2026-16204?** Medium severity, with a CVSS score of 6.3, published 19 July 2026.

**Which products and versions are affected?** Zevorn Rt-Claw up to 0.2.0 and unreleased upstream commits.

**Is there a fix for CVE-2026-16204?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-16204 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-16204?** Check whether you run Zevorn Rt-Claw at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

A code injection vulnerability exists in the Telegram-to-AI Tool Execution Flow of zevorn rt-claw. The root cause is the lack of an approval mechanism or 'deny-by-default' policy in the tool dispatch loop within `claw/services/tools/script.c`. When a remote Telegram user sends a message that causes the AI model to return a `run_script` tool call, the `tool_run_script_execute` function immediately executes the provided Python code via the Linux platform backend. An attacker can exploit this by influencing the AI model to trigger the `run_script` tool, resulting in arbitrary code execution with the privileges of the rt-claw process. As of the advisory date, the project has not responded to the issue report.

## Affected products

- zevorn rt-claw up to 0.2.0 and unreleased upstream commits

## Timeline

- 2026-07-18: disclosed: Vulnerability reported via GitHub issue #138
- 2026-07-19: advisory: CVE-2026-16204 published

## References

- [https://github.com/zevorn/rt-claw/](https://github.com/zevorn/rt-claw/)
- [https://github.com/zevorn/rt-claw/issues/138](https://github.com/zevorn/rt-claw/issues/138)
- [https://vuldb.com/cve/CVE-2026-16204](https://vuldb.com/cve/CVE-2026-16204)
- [https://vuldb.com/submit/857784](https://vuldb.com/submit/857784)
- [https://vuldb.com/vuln/380020](https://vuldb.com/vuln/380020)
- [https://vuldb.com/vuln/380020/cti](https://vuldb.com/vuln/380020/cti)

## Related threats

- [zevorn rt-claw information disclosure in http_request tool](https://junglewise.ai/threats/cve-2026-16201-zevorn-rt-claw-information-disclosure-in-http-request-tool)
- [zevorn rt-claw incorrect authorization in RPC Handler](https://junglewise.ai/threats/cve-2026-16200-zevorn-rt-claw-incorrect-authorization-in-rpc-handler)
- [zevorn rt-claw SSRF in swarm RPC service](https://junglewise.ai/threats/cve-2026-16128-zevorn-rt-claw-ssrf-in-swarm-rpc-service)
- [zevorn rt-claw SSRF in http_request tool](https://junglewise.ai/threats/cve-2026-16127-zevorn-rt-claw-ssrf-in-http-request-tool)
- [zevorn rt-claw incorrect authorization in Swarm RPC Receiver](https://junglewise.ai/threats/cve-2026-16126-zevorn-rt-claw-incorrect-authorization-in-swarm-rpc-receiver)