CVE-2026-45792

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.

CVSS

No CVSS.

References

Link	Resource
https://github.com/rtk-ai/rtk/pull/623
https://github.com/rtk-ai/rtk/pull/625
https://github.com/rtk-ai/rtk/security/advisories/GHSA-fvvm-949w-qj4w

Configurations

No configuration.

History

23 Jun 2026, 20:16

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-06-23 20:16

Updated : 2026-06-23 20:16

NVD link : CVE-2026-45792

Mitre link : CVE-2026-45792

CVE.ORG link : CVE-2026-45792

JSON object : View

Products Affected

No product.

CWE

CWE-345

Insufficient Verification of Data Authenticity

CWE-426

Untrusted Search Path

{"id": "CVE-2026-45792", "cveTags": [], "metrics": {"cvssMetricV40": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 6.9, "Automatable": "NOT_DEFINED", "attackVector": "LOCAL", "baseSeverity": "MEDIUM", "valueDensity": "NOT_DEFINED", "vectorString": "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", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "ACTIVE", "attackComplexity": "LOW", "attackRequirements": "PRESENT", "privilegesRequired": "NONE", "subIntegrityImpact": "HIGH", "vulnIntegrityImpact": "HIGH", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "NONE", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "HIGH", "vulnConfidentialityImpact": "NONE", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "rtk-ai", "product": "rtk", "versions": [{"status": "affected", "version": "< 0.32.0"}]}]}], "published": "2026-06-23T20:16:47.850", "references": [{"url": "https://github.com/rtk-ai/rtk/pull/623", "source": "security-advisories@github.com"}, {"url": "https://github.com/rtk-ai/rtk/pull/625", "source": "security-advisories@github.com"}, {"url": "https://github.com/rtk-ai/rtk/security/advisories/GHSA-fvvm-949w-qj4w", "source": "security-advisories@github.com"}], "vulnStatus": "Received", "weaknesses": [{"type": "Primary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-345"}, {"lang": "en", "value": "CWE-426"}]}], "descriptions": [{"lang": "en", "value": "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."}], "lastModified": "2026-06-23T20:16:47.850", "sourceIdentifier": "security-advisories@github.com"}