# 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.

- **Severity:** Medium 6.9 (`CVSS:4.0/AV:L/AC:L/AT:P/PR:N/UI:A/VC:N/VI:H/VA:N/SC:H/SI:H/SA:N`)
- **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:** Yes
- **Published:** 23 Jun 2026
- **Updated:** 26 Jun 2026
- **Also known as:** GHSA-fvvm-949w-qj4w

## 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.

Weakness: CWE-426 (Untrusted Search Path), CWE-345 (Insufficient Verification of Data Authenticity)

## Which versions are affected by CVE-2026-45792?

2 open source packages ship an affected version, including rtk. It affects 1 product.


| Package | Ecosystem | Affected | Fixed in |
| --- | --- | --- | --- |
| `rtk` | crates.io | All versions | 0.32.0 |
| `rtk` | crates.io | All versions | 0.32.0 |

Products: 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.

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-45792 and fix it if it is affected.

What it is: 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.
Exploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-45792 exists.

Affected packages and fixed versions:
- rtk (crates.io): affected all versions; fixed in 0.32.0
- rtk (crates.io): affected all versions; fixed in 0.32.0

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-45792/ (Markdown: https://insights.sbomify.com/CVE-2026-45792/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-45792
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-45792
- OSV: https://osv.dev/vulnerability/CVE-2026-45792

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-45792/
Summaries are generated and may contain mistakes; the official description above is the record.