Raw vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:HSummary
CVE-2025-58370 is a high-severity OS Command Injection (CWE-78) vulnerability in Roocode Roo Code. Its CVSS base score is 8.1 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked at the 36th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the LLM/Generative AI Risks risk domain.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2025-58370 affects Roo Code, an AI-powered autonomous coding agent integrated into users' editors, in versions below 3.26.0. The vulnerability resides in the command parsing logic, where Bash parameter expansion and indirect references are not handled correctly, enabling a form of command injection classified under CWE-78. This flaw has a CVSS v3.1 base score of 8.1 (AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H), indicating high severity due to potential for significant confidentiality, integrity, and availability impacts.
An attacker who can influence the prompts provided to the agent could exploit this issue if the agent is configured to auto-approve execution of certain commands. By crafting malicious prompts, the attacker can abuse the parsing weakness to execute additional arbitrary commands alongside the intended one, potentially leading to full system compromise on the developer's machine where the agent runs.
The vulnerability is addressed in Roo Code version 3.26.0, as detailed in the security advisory at https://github.com/RooCodeInc/Roo-Code/security/advisories/GHSA-2rm5-cvcm-7592. Security practitioners should urge users to update to 3.26.0 or later and review configurations to disable auto-approval of command executions where possible.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-27162
Vulnerability Data
Roo Code is an AI-powered autonomous coding agent that lives in users' editors. Versions below 3.26.0 contain a vulnerability in the command parsing logic where the Bash parameter expansion and indirect reference were not handled correctly. If the agent was…
more
configured to auto-approve execution of certain commands, an attacker able to influence prompts could abuse this weakness to execute additional arbitrary commands alongside the intended one. This is fixed in version 3.26.0.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.2.5V1.2.8V15.2.5
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation can discover missing or incorrect command sanitization during development.
Input validation directly neutralizes or rejects special characters that would otherwise alter OS command structure.
Least privilege reduces the permissions available to any process that could be subverted by injected commands.
Least functionality restricts available OS commands and interpreters, limiting the blast radius of injection.
Secure engineering principles require proper neutralization of untrusted input before command construction.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
PR.PS-06's SDLC practices directly require secure coding and input handling that blocks command-injection defects, yet the single broad outcome leaves many specific neutralization vectors and verification gaps unaddressed.
Routine patching/maintenance can remediate known command-injection CVEs in dependencies (partial forward) but does nothing to stop developers from introducing improper neutralization in custom code (none reverse).
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing and code review target insecure use of operating-system command interfaces, catching command-injection flaws introduced during development.