ClawHub
Back to skill

Security audit

质量功能展开技能

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent QFD quality-planning helper that uses local, user-directed files and scripts without hidden network, credential, persistence, or destructive behavior.

Before installing, treat VOC and historical project files as potentially sensitive: minimize or anonymize customer and business data, and run the scripts only against intended local input and output paths.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs use of local scripts and file-based inputs/outputs, which implies file read/write capabilities, yet it declares no permissions or safety boundaries. This can lead to over-privileged or opaque execution behavior, making it harder for a host system or user to understand and constrain what files may be accessed or modified.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger conditions are broad enough to activate on common quality-planning or prioritization requests without clear boundaries, which can cause the skill to engage in contexts the user did not intend. Over-broad invocation increases the chance of unnecessary data handling or unintended script/file operations associated with the skill workflow.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly processes customer feedback and historical project data, both of which may contain personal, confidential, or commercially sensitive information, but it provides no privacy or data-handling warning. In practice this can lead users to expose sensitive datasets without minimization, masking, retention limits, or consent checks.

Static analysis

No suspicious patterns detected.