ClawHub
Back to skill

Security audit

Event Staffing Procurement

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed TempGuru procurement and staffing-planning helper that uses an external MCP service for policy, planning, and quote-form handoff without hidden code or persistence.

Install only if you are comfortable using TempGuru's external MCP service for procurement answers and event staffing plans. Keep contact details out of MCP requests and enter them only on the TempGuru-owned form after reviewing the returned plan.

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 (1)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill is presented as a narrow procurement and policy-answering agent, but its sole MCP dependency is described as providing broader capabilities including planning, pricing, compliance, and quote tools. That creates a scope mismatch: if the model can access tools outside the declared purpose, prompt injection, user confusion, or orchestration mistakes could cause actions or disclosures beyond what users and reviewers expect.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.