ClawHub
Back to skill

Security audit

solo-build-free

Security checks across malware telemetry and agentic risk

Overview

This skill is a plausible build-automation helper, but it can automatically change code, run shell commands, commit changes, and use git checkout rollback with too little user control.

Review before installing. Use this only in repositories where you are comfortable with an agent editing files, running local commands, and creating commits. Keep a clean working tree or backup branch first, and do not allow rollback commands such as git checkout unless you explicitly approve them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The activation scope is broad enough to match common coding, debugging, testing, and deployment-related prompts, increasing the chance the skill is invoked in situations where users did not intend automated file modification or command execution. In a skill with exec/write capabilities and autonomous workflow steps, overbroad triggering materially raises the risk of unintended high-impact actions.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill is designed to change files, update plan state, and create git commits automatically, but the description does not prominently warn users about those repository-modifying actions. In the context of a build-execution skill with write and exec tools, lack of explicit notice increases the risk of silent or surprising changes to project state and audit history.

Missing User Warnings

High
Confidence
96% confidence
Finding
The workflow includes running shell commands such as tests and integration checks, yet the skill description does not clearly warn that command-line operations will be executed. Because the skill has exec capability, hidden or under-disclosed command execution is dangerous: users may trigger shell actions without understanding the operational or security consequences.

Missing User Warnings

High
Confidence
97% confidence
Finding
The failure-handling guidance includes rollback behavior using git checkout, which can discard local changes, but the skill does not prominently warn about this potentially destructive repository operation. In a tool that autonomously executes workflows, undisclosed rollback capability can lead to data loss, corrupted work-in-progress, or unexpected repository state changes.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.