ClawHub
Back to skill

Security audit

math-docx-typeset

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent math-to-Word converter with disclosed local file processing and no evidence of hidden persistence, exfiltration, or destructive behavior.

Install only if you need math/formula-heavy docx generation. Review the PyPI dependencies before installing, invoke the skill specifically for formula conversion, and avoid sending confidential screenshots through cloud OCR unless you are comfortable with that data flow.

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
80% confidence
Finding
The skill instructs the agent to read multiple local reference files and invoke a local conversion script, which implies file-read capability without an explicit permission declaration. Undeclared file access increases the risk of overbroad data exposure because the runtime or reviewers cannot clearly constrain what files the skill is expected to access.

Vague Triggers

Medium
Confidence
75% confidence
Finding
The activation phrases include broad expressions such as '生成 docx' and '写论文 docx', which can cause the skill to trigger in unrelated conversations. Over-triggering can route user content into file-processing workflows unexpectedly, increasing the chance of unintended file access or document generation actions.

Static analysis

No suspicious patterns detected.