Command Injection in FoundDream miniclawd Skills Loader

A vulnerability was detected in FoundDream miniclawd up to 2d65665046e2222eeea76cafc8570ed546a8c125. This affects the function which of the file /src/application/skills-loader.ts of the component SkillsLoader. Performing a manipulation of the argument requires.bins results in command injection. The attack may be initiated remotely. The exploit is now public and may be used. This product uses a rolling release model to deliver continuous updates. As a result, specific version information for affected or updated releases is not available. The project was informed of the problem early through an issue report but has not responded yet.

Casky was already ahead

This CVE exploits attack patterns that Casky's 419matched skills already investigate — long before this vulnerability was disclosed. Claude's reasoning model maps these techniques to MITRE ATT&CK, so practitioners who ran these skills have already seen the threat behaviour in their findings.

Analysis

CVE-2026-9453 represents a critical command injection vulnerability in the SkillsLoader component of FoundDream miniclawd, where unsanitized manipulation of the requires.bins argument enables remote code execution. This high-severity flaw (CVSS 7.3) affects systems using the vulnerable version of the skills-loader.ts module, creating immediate risk for any organization deploying this component in their security automation pipelines. With public exploit code now available, threat actors can leverage this vulnerability to gain unauthorized command execution and potentially compromise the integrity of security skill definitions and threat detection workflows.

Casky's 419 matched skills leverage Claude AI's extended reasoning to detect the attack patterns underlying this CVE by analyzing activity across MITRE ATT&CK techniques TA0001 (Reconnaissance), TA0043 (Reconnaissance), and TA0002 (Resource Development). Practitioners using Casky would observe detection patterns for CWE-74 and CWE-77 violations—improper neutralization of special elements in output and command construction. When monitoring for this vulnerability, security teams would see skills identifying suspicious argument manipulation in requires.bins parameters, unusual child process creation from the SkillsLoader component, and anomalous command invocations that deviate from legitimate skill loading patterns. Claude's reasoning capability allows these skills to correlate multiple signals—from input validation bypasses to unexpected system calls—providing practitioners with high-confidence alerts that distinguish exploitation attempts from normal skill loader operations.

Live Threat IntelligenceComing soon

Casky Risk Score

—

EPSS Probability

—

Shodan Exposure

—

GreyNoise Signal

—

Composite risk scoring from EPSS, CISA KEV, Shodan, and GreyNoise — 21 security APIs correlated into a single Casky Risk Score. Coming in Casky Pro. Join early access →

419 Casky skills cover this attack pattern

These skills use Claude AI's reasoning model to surface findings in the same attack categories as CVE-2026-9453.

analyzing-android-malware-with-apktool

malware analysis · medium

Run

analyzing-apt-group-with-mitre-navigator

threat intelligence · low

Run

analyzing-bootkit-and-rootkit-samples

malware analysis · medium

Run

MITRE ATT&CK Techniques

TA0001 TA0043 TA0002

Investigate the attack patterns behind CVE-2026-9453

Casky has 419 skills that investigate the attack patterns behind CVE-2026-9453. Run one and get CVSS-scored findings in 3 minutes.

Run the skill that detects this →

X Instagram LinkedIn