ClawHub
Back to skill

Security audit

Military PCS Optimizer

Security checks for vulnerabilities and agentic risk

Overview

The skill is markdown-only and not technically dangerous, but it overstates its PCS calculator/planner capabilities while directing users to a paid external version for major promised features.

Review this as an incomplete PCS overview with an external paid upsell, not as a reliable installed calculator. Do not rely on it for official reimbursement, allowance, tax, or PCS planning decisions without checking current DoD or service-specific sources.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest and top-level description present the skill as a comprehensive PCS calculator and planner, but the file later reveals that substantial functionality is withheld behind an external paid offering. This is a deceptive capability mismatch that can mislead users into relying on incomplete guidance and funnel them to an off-platform purchase, which is especially concerning in a financial/benefits context where accuracy and completeness materially affect decisions.

Intent-Code Divergence

Low
Confidence
91% confidence
Finding
Claiming the skill is the 'most comprehensive PCS skill available' is inconsistent with later disclosures that this edition is only an overview and omits major content. While mostly a trust and integrity issue rather than direct code execution risk, it can still deceive users about the completeness and reliability of the advice they are receiving.

Static analysis

No suspicious patterns detected.