ClawHub
Back to skill

Security audit

HRBP Weekly Decision Brief

Security checks for vulnerabilities and agentic risk

Overview

This skill is a bounded HR briefing workflow with clear human-review safeguards and only a local structural checker.

Install only if you are comfortable using it for HR-related draft preparation. Provide minimized, approved source packets, keep drafts marked for human review, and do not use the structural checker as proof that facts, policy, legal issues, or employment decisions are correct.

SkillSpector

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
This is a mismatch because the description says the skill creates weekly HRBP decision briefs, but the code does not generate or assemble any brief content. Its primary function is a linter/validator that inspects an existing markdown file for structural completeness only. While the validation supports human review, the core behavior materially differs from the declared purpose of creation.

Static analysis

No suspicious patterns detected.