CVE-2026-45792 RTK improperly trusts project-local filter configuration, allowing silent tampering of command output shown to LLM
- Published
- Updated
- Exploit status
- No public exploit known
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.
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| rtk-ai rtk | = < 0.32.0 | No fix listed |
| crates.io rtk(crates.io) | < 0.32.0 | 0.32.0 |
| rtk-ai rtk | < 0.32.0 | 0.32.0 |
References
- https://github.com/rtk-ai/rtk/security/advisories/GHSA-fvvm-949w-qj4w patch vendor-advisory
- https://github.com/rtk-ai/rtk/pull/623 exploit issue-tracking patch
- https://github.com/rtk-ai/rtk/pull/625 issue-tracking patch
- nvd.nist.gov third-party-advisory vendor-advisory
- github.com product
- github.com