ClawHub
Back to skill

Security audit

req-to-testcase

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims, but users should be aware it can read uploaded requirement documents and create XMind output files.

Install only if you want a skill that reads uploaded requirement documents and generates test-case/XMind files. Use it with explicit prompts, avoid feeding sensitive spreadsheets unless intended, and install dependencies in an isolated Python environment.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill instructs the agent to read uploaded files and generate an output file, which are file_read and file_write capabilities, but no permissions are declared. This creates a governance gap: the runtime may execute sensitive file operations without explicit scoping, review, or user-visible consent boundaries.

Description-Behavior Mismatch

Medium
Confidence
83% confidence
Finding
The manifest advertises only Word/PDF/Markdown/TXT inputs, but the implementation also processes Excel and CSV files. This mismatch can cause the skill to ingest data types users or reviewers did not expect, increasing the risk of accidental processing of sensitive tabular data and weakening trust in the declared scope.

Vague Triggers

High
Confidence
91% confidence
Finding
The trigger rules are overly broad: any uploaded document plus common words like 'test', 'case', 'XMind', or 'coverage' can force activation. In a multi-skill environment, this can cause unintended invocation on unrelated or sensitive documents, leading to unnecessary file access, data exposure to the skill, and incorrect automation.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The statement that the skill 'must' trigger for uploaded requirement documents is ambiguous because it does not define scope, document classes, or exclusions. That ambiguity can cause the agent to over-apply the skill, especially when the uploaded file is only partially related, increasing unnecessary data access and reducing user control.

Static analysis

No suspicious patterns detected.