ClawHub
Back to skill

Security audit

质量管理QC技能

Security checks for vulnerabilities and agentic risk

Overview

This QC chart skill is a coherent local analysis tool that generates charts and optional JSON output from user-provided quality data.

Before installing, be aware that the tool runs a local Python script and writes chart files to the path you provide. Use a project or output directory you control, avoid sensitive filenames or broad system paths, and only provide quality-analysis data you intend to process locally.

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
84% confidence
Finding
The skill instructs the agent to run a local Python script and write outputs, which implies file read/write behavior, but no permissions are declared. This creates a trust and policy gap: an agent may access local files or write artifacts without explicit user-visible authorization boundaries.

Vague Triggers

Medium
Confidence
77% confidence
Finding
The trigger condition covers very broad situations like any quality analysis, diagnosis, visualization, process control, or correlation analysis, without clear exclusion criteria. Over-broad activation can cause the skill to run in unintended contexts, increasing the chance of inappropriate file operations or script execution on unrelated user requests.

Static analysis

No suspicious patterns detected.