ClawHub
Back to skill

Security audit

AgentVibes内容技能

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a content/API wrapper, but it asks for broad local file and command-execution authority without a clear need.

Review this skill carefully before installing. It may be useful for AgentVibes content workflows, but only grant local file or command-execution access if you specifically need those functions and can supervise what commands or files it touches. Store any API key in an environment variable and avoid using it in workspaces containing sensitive files unless the tool scope is restricted.

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The skill is presented as a content/API wrapper, but later documentation advertises file handling, command execution, and system-oriented operations that are unrelated to the declared purpose. This mismatch can mislead an agent into granting or using broader capabilities than necessary, increasing the attack surface for unsafe local actions.

Context-Inappropriate Capability

High
Confidence
95% confidence
Finding
Command execution is a high-risk capability and is not justified by a skill whose stated purpose is content generation through external APIs. If an agent relies on this documentation, it may execute local commands unnecessarily, enabling command injection, file tampering, or environment inspection beyond the user's expected scope.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The activation condition is vague and overly broad, including a trigger tied to a generic user phrase rather than precise task intent. Ambiguous invocation can cause the skill to activate in unintended contexts, especially dangerous when the skill also declares powerful capabilities like read/write/exec.

Static analysis

No suspicious patterns detected.