CVE-2026-45792 RTK improperly trusts project-local filter configuration, allowing silent tampering of command output shown to LLM
Attackers can tamper with command output shown to LLMs via malicious project-local config files, concealing malicious code during AI-assisted development.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- A user has to click or open something
- Fix
- Available
What is CVE-2026-45792?
CVE-2026-45792 is a medium-severity vulnerability in rtk-ai rtk, published on 23 Jun 2026. It can only be exploited from the same machine or local network, and only if a user opens a file or follows a link.
Official description
rtk filters and compresses command outputs before they reach your LLM context. Prior to 0.32.0, RTK (Rust Token Killer) improperly trusts project-local configuration files. RTK automatically loads .rtk/filters.toml from the working directory with highest priority and without user notification. An attacker can place a malicious filter file in a repository to apply regex-based modifications (e.g., strip_lines_matching) to shell command output before it is shown to the LLM, without any indication that the output has been modified. This allows attackers to selectively suppress or alter command output (including file contents, diffs, and security scan results) without detection, potentially concealing malicious code during AI-assisted development or review. This vulnerability is fixed in 0.32.0.
Which versions are affected by CVE-2026-45792?
2 open source packages ship an affected version, including rtk. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
rtk crates.io | All versions | 0.32.0 |
rtk crates.io | All versions | 0.32.0 |
Products include Rtk-Ai Rtk.
How do I fix CVE-2026-45792?
Upgrade rtk to 0.32.0 or later.
Is CVE-2026-45792 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-45792 exists.
Sources
Also known as GHSA-fvvm-949w-qj4w.