Back to skill

Security audit

HRBP Weekly Decision Brief

Security checks for vulnerabilities and agentic risk

Overview

This skill creates draft HR decision briefs with explicit privacy limits and human-review controls, without hidden persistence or external actions.

Installers should treat this as an HR drafting aid only. Use synthetic, de-identified, or explicitly approved source packets; do not let it make employment decisions, send communications, update HR systems, or retain named-person profiles.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared description says the skill creates weekly HRBP decision briefs for human review. The code instead acts as a checker: it reads a specified markdown file, ensures required sections and decision-item fields exist, rejects placeholder/unresolved values, and confirms the document remains marked as draft for human review. This is a materially different primary purpose from creation/generation. The human-review aspect is partially aligned, but the implementation is a structural completeness gate, not a brief-creation tool, and it does not inspect or verify underlying sources beyond requiring a 'Source references' field.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.