ClawHub
Back to skill

Security audit

chief-creative-officer

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly a creative-strategy prompt, but it asks for broad read/write/command authority and describes API automation without clear limits.

Review before installing. The visible content does not show malware or destructive instructions, but a user should only enable it if they are comfortable with a creative assistant that can potentially read/write files, run commands, and use external services. Prefer restricting it to creative documents and require explicit approval before any file mutation, shell command, callback URL, or API-key-backed operation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
This skill is presented as a creative strategy and brand storytelling tool, yet it declares file processing, external API integration, and command execution capabilities that materially exceed what is needed for its stated purpose. That mismatch expands the attack surface: a user invoking a seemingly benign creativity skill could be induced to read/write files or execute shell commands under broad productivity pretexts.

Intent-Code Divergence

Low
Confidence
78% confidence
Finding
The documentation first states that no additional API key is required, but later says some features do require platform-specific API keys. This inconsistency can mislead users about networked behavior and credential handling, increasing the risk of accidental secret exposure or unexpected external service use.

Vague Triggers

High
Confidence
90% confidence
Finding
The invocation guidance is overly broad, recommending the skill for generic efficiency, automation, batch processing, and workflow optimization tasks rather than narrowly scoped creative work. In context, that broad framing is especially risky because the skill also has read/write/exec capabilities, making it easier to socially engineer use for unrelated operational tasks with side effects.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill advertises file writes, command execution, and external/API-style operations without clear, prominent warnings about filesystem changes, command side effects, or data leaving the environment. Given the benign creative branding, users may not reasonably expect these capabilities, which increases the chance of unsafe invocation and privilege misuse.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.