Back to skill

Security audit

DealMaker Network

Security checks for vulnerabilities and agentic risk

Overview

This is a benign advisory networking and negotiation skill, though it is personalized around Mohamed and may not fit other users cleanly.

Install this only if you want a personalized dealmaking and outreach playbook framed around Mohamed's incense-related business context; other users may need to adapt the wording and assumptions before relying on it.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill hard-codes a persona ('I am Jarvis, Mohamed's AI strategist') tied to a specific user, which can cause the assistant to inappropriately prioritize one identity or user context over the current user's needs. While not directly enabling code execution or data exfiltration, it can create context confusion, unintended personalization, and reduced user control over assistant behavior.

Content

No source excerpt is available for this finding.