Auth bypass in Rtk-Ai Rtk
CVE-2026-54555
rtk filters and compresses command outputs before they reach your LLM context. Prior to 0.42.2, the permission splitter did not conservatively split or reject several shell constructs that Bash treats as command execution boundaries or nested execution. As a result, a command beginning with an allowed prefix such as git could hide a second command behind one of these constructs. rtk rewrite returned exit code 0, causing the Claude hook to emit permissionDecision: "allow". The rewritten command still contained the hidden command, so it ran without the user confirmation or denial that the permission rules were intended to enforce. This vulnerability is fixed in 0.42.2.
Vulnerability class: Broken Access Control
EPSS: 0.002 (9.6th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 7.8 (High). Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
Affected products
- Rtk-ai Rtk — versions < 0.42.2
Weakness classification (CWE)
References
- security-advisories@github.com (x_refsource_CONFIRM)
Frequently asked questions
- What is CVE-2026-54555?
- CVE-2026-54555 is a high-severity vulnerability in Rtk-Ai Rtk, classified under Incorrect Authorization. CVSS score: 7.8/10. Published 2026-06-23.
- How severe is CVE-2026-54555?
- High severity. CVSS v3 base score is 7.8 out of 10.