CVE-2026-54555
rtk: Permission-gate bypass in rtk rewrite auto-allow via unsplit shell separators
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.
INFO
Published Date :
June 23, 2026, 8:16 p.m.
Last Modified :
June 25, 2026, 8:18 p.m.
Remotely Exploit :
No
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | HIGH | [email protected] |
Solution
- Update the software to version 0.42.2 or later.
- Review and enforce stricter parsing of shell constructs.
- Verify command execution boundaries and permissions.
- Implement robust security checks for all commands.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-54555.
| URL | Resource |
|---|---|
| https://github.com/rtk-ai/rtk/security/advisories/GHSA-7gxq-fvfc-g327 | |
| https://github.com/rtk-ai/rtk/security/advisories/GHSA-7gxq-fvfc-g327 |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-54555 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-54555
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-54555 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-54555 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 24, 2026
Action Type Old Value New Value Added Reference https://github.com/rtk-ai/rtk/security/advisories/GHSA-7gxq-fvfc-g327 Added SSVC {'id': 'CVE-2026-54555', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'no'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-06-24T14:29:21.375030Z'} -
New CVE Received by [email protected]
Jun. 23, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'rtk-ai', 'product': 'rtk', 'versions': [{'status': 'affected', 'version': '< 0.42.2'}]}] Added 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. Added CVSS V3.1 AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Added CWE CWE-863 Added Reference https://github.com/rtk-ai/rtk/security/advisories/GHSA-7gxq-fvfc-g327