ClawHub
Back to skill

Security audit

Code Dev V1

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed development and release-management helper whose command and CI/CD examples fit its stated purpose, though users should review actions before running them.

Before installing, understand that this skill may guide an agent to run shell commands, create local .code-toolkit files, manage Git release state, and optionally use CI/CD tokens or webhooks. Review commands before execution, keep credentials in protected environment variables or a secret manager, and require explicit approval for staging or production release actions.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly declares the `exec` tool and later documents operational workflows that can execute commands, but it does not provide a clear user-facing warning that command execution may modify the local system, repository state, or trigger external actions. In an agent setting, normalizing command execution without explicit consent and risk disclosure increases the chance that a user invokes destructive or sensitive operations unintentionally.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This section includes filesystem-modifying shell commands such as `mkdir -p` and writing configuration files with `cat > ...`, but presents them as routine setup without a warning about side effects. In an agent-driven environment, such instructions can lead to unauthorized workspace changes, accidental overwrites, or persistence of operational metadata without the user's informed approval.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill documents exporting a CI token and a release webhook, but does not warn about secret exposure, shell history leakage, log capture, or outbound network effects when those credentials are later used. In a deployment-oriented skill with `exec` capability, this creates real risk of credential mishandling and unintended communication with external systems.

Static analysis

No suspicious patterns detected.