CVE-2026-45792

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

Published Jun 23, 2026 CVSS 4.0 · 6.9 Medium EPSS < 1% KEV · Not listed
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.

Remediation

No solution or workaround provided in the CVE record

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
Github GHSA Github GHSA GHSA-fvvm-949w-qj4w RTK improperly trusts project-local filter configuration, allowing silent tampering of command output shown to LLM
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Rtk-ai
Rtk-ai rtk
Vendors & Products Rtk-ai
Rtk-ai rtk
Type Values Removed Values Added
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.
Title RTK improperly trusts project-local filter configuration, allowing silent tampering of command output shown to LLM
Weaknesses CWE-345
CWE-426
References
Metrics cvssV4_0

{'score': 6.9, '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'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Jun 26, 2026, 3:18 PM
Reserved
May 13, 2026, 8:19 AM
Status
Analyzed
Published
Jun 23, 2026, 8:16 PM
Modified
Oct 25, 2026, 11:10 PM