ClawHub
Back to skill

Security audit

skill-creater

Security checks across malware telemetry and agentic risk

Overview

This skill is a local helper for creating and packaging other skills, with expected file-writing behavior and no evidence of credential access, exfiltration, or destructive actions.

Install only if you are comfortable with a skill that creates local files and zip archives. Use it on a dedicated clean folder, inspect generated files and zip contents before uploading, and avoid running the included build.sh unless you first fix its name/path mismatch.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill explicitly claims it will generate files, create directory structures, and package them into a zip archive, which implies file read/write behavior, yet no permissions are declared. This creates a capability/permission mismatch that can lead users or host systems to grant or execute filesystem actions without clear authorization boundaries, especially in a meta-skill that produces and packages artifacts automatically.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The description is broad enough to trigger on common requests like creating a new skill, building a custom skill, or packaging an existing skill, which can cause the skill to activate in situations where the user did not intend broad generation or packaging behavior. For a skill that can create files and archives, overbroad invocation increases the chance of unintended execution, confusing delegation, or misuse as a generic code/content generation tool.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.