ClawHub
Back to skill

Security audit

content-formatter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a content formatter whose disclosed Python execution and optional file input fit its stated formatting purpose.

Install this if you need platform-specific content formatting. Only pass --content-file paths for documents you intend to format, since the tool will read and return the supplied file's content in formatted output.

SkillSpector

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
94% confidence
Finding
The skill declares no explicit permissions, yet its manifest and documentation indicate use of `subprocess`, `python`, shell commands, and file-based content input. This creates a capability/permission mismatch that can mislead reviewers and downstream policy enforcement, increasing the risk of unintended file access or command execution through a formatting skill that appears low-risk.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger phrases are very broad (`内容排版/格式转换/平台适配`), which can cause the skill to activate for many generic user requests unrelated to this specific formatter. Overbroad activation increases attack surface because a shell-capable skill may be selected more often than necessary, exposing file-reading and subprocess behaviors in contexts where a simpler, safer path would suffice.

Static analysis

No suspicious patterns detected.