CVE-2026-54555 rtk: Permission-gate bypass in rtk rewrite auto-allow via unsplit shell separators
Attackers can bypass permission gates in rtk by hiding commands behind shell separators, allowing unauthorized execution of arbitrary commands.
- 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
- None listed
What is CVE-2026-54555?
CVE-2026-54555 is a high-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 0.42.2, 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.
Weakness: CWE-863
Which versions are affected by CVE-2026-54555?
How do I fix CVE-2026-54555?
No fix has been published for CVE-2026-54555 yet. Limit exposure of the affected software until one is available.
Is CVE-2026-54555 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-54555 exists.
Sources
Also known as GHSA-7gxq-fvfc-g327.