ClawHub
Back to skill

Security audit

skill9

Security checks for vulnerabilities and agentic risk

Overview

This is a plausible cloud skill-backup tool, but it asks agents to broadly and automatically sync local skill files to a cloud service with limited user-facing scoping or privacy detail.

Review this carefully before installing. Use it only if you are comfortable sending local skill files to skill9's cloud, verify the npm package and GitHub login scopes, check your skills for secrets or proprietary content, and inspect or disable any AGENTS.md rules or Claude/Cursor hooks if you do not want ongoing automatic syncing.

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
96% confidence
Finding
The setup flow instructs the agent to run an initial backup upload immediately after login, but it does not disclose that local skill contents may be transmitted to a remote service. Because skills can contain prompts, proprietary logic, secrets, or sensitive local configuration, silent upload behavior creates a meaningful privacy and data-exfiltration risk.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The auto-backup rules mandate pushing after every skill creation, edit, install, or deletion, which normalizes continuous remote transmission of local skill state without any privacy disclosure or approval checkpoint. In the context of an agent skill vault that operates across multiple platforms and common skill directories, this increases the chance of repeatedly syncing sensitive or unintended content to the service.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises cloud backup, sync, pull, rollback, and deletion operations but provides no warning that data will be transferred off-host or that some commands can modify or remove remote/local state. In an agent context, this can cause unintended exfiltration of skill contents or destructive actions if a user invokes commands without understanding their effects.

Static analysis

Detected: suspicious.destructive_delete_command

Documentation contains a destructive delete command without an explicit confirmation gate.

Warn
Code
suspicious.destructive_delete_command
Location
UNINSTALL.md:43