CVE-2026-45792 json
RTK improperly trusts project-local filter configuration, allowing silent tampering of command output shown to LLM
published 2026-05-20 5 mo ago modified 2026-10-25 14 d ago also GHSA-fvvm-949w-qj4w , EUVD-2026-38572
- cvss
- 5.5
- version 3.1, NVD
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.1%
- EPSS 0.1% chance of exploitation in 30 days, percentile 1%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
- crates.io rtk 0.32.0
- rtk-ai rtk 0.32.0
- github.com/rtk-ai/rtk#625 pull request
- github.com/rtk-ai/rtk/security/advisories/GHSA-fvvm-949w-qj4w advisory
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- partial
- Assessed
- 4 mo ago
Exploit prediction
0.11% chance of exploitation in the next 30 days, higher than 1% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/rtk-ai/rtk/pull/623 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 6.9 | 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 |
| CNA | 4.0 | 6.9 | 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
| NVD | 3.1 | 5.5 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N |
| GitHub | 3.1 | 5.5 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| crates.io | rtk | <0.32.0 |
0.32.0 |
Affected products
- rtk-ai rtk
Classification
References
-
github.com
/rtk-ai/rtk/pull/623
exploit, web, issue-tracking
-
github.com
/rtk-ai/rtk/pull/625
web, issue-tracking
-
github.com
/rtk-ai/rtk/security/advisories/GHSA-fvvm-949w-qj4w
web, patch, vendor-advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-45792
advisory
-
github.com
/rtk-ai/rtk
package
Sources
- CVE List CVE-2026-45792
- GitHub Advisory GHSA-fvvm-949w-qj4w
- NVD CVE-2026-45792
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.