ClawHub
Back to skill

Security audit

Creative Officer

Security checks for vulnerabilities and agentic risk

Overview

The skill is mainly a creative planning assistant, but its manifest grants read, write, and command execution powers that are broader than its stated Markdown-only purpose.

Review this skill before installing. Its creative-planning content does not appear malicious, but install it only if you are comfortable granting broad file and command authority, or ask the publisher to remove exec/write or add explicit scopes and approval requirements.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Intent-Code Divergence

High
Confidence
95% confidence
Finding
The skill claims to be a pure Markdown skill that does not require exec, yet the manifest exposes exec and the feature list advertises command execution. This mismatch can hide powerful execution capability behind a low-risk description, increasing the chance that users or orchestration systems invoke it with more trust than warranted.

Context-Inappropriate Capability

High
Confidence
96% confidence
Finding
The manifest grants read, write, and exec capabilities even though the documented purpose is creative planning and brand management. Excessive privileges violate least privilege and could enable file tampering, data exposure, or arbitrary command execution if the skill is misused, prompted maliciously, or compromised.

Description-Behavior Mismatch

High
Confidence
94% confidence
Finding
The skill's stated role is strategic creative assistance, but it also claims generic file processing, API integration, and command execution capabilities. Broad operational capabilities unrelated to the core business function expand the attack surface and make prompt-induced misuse more dangerous.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill exposes file write, external API, and command execution capabilities without a clear user warning in the Markdown guidance. Hidden or under-disclosed powerful actions increase the risk of users invoking a seemingly harmless creative-planning skill that can perform sensitive system operations.

Static analysis

No suspicious patterns detected.