Log in Start free

Vulnerability · Published Jun 23, 2026 · Assigned by GitHub_M

CVE-2026-45792RTK improperly trusts project-local filter configuration, allowing silent tampering of command output shown to LLM

Medium 6.9

In plain English

A medium-severity insufficient verification of data authenticity in rtk from rtk-ai. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.1% (higher than 1% of all known vulnerabilities).

Severity (CVSS 4.0)6.9Medium
Exploit odds (30 days)0.1%top 98.7% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

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.

Affected products (as reported)

VendorProductVersions
rtk-ai rtk < 0.32.0

Weakness: CWE-345, CWE-426 · Vector: 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

References