Back to skill

Security audit

Diddy Party

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed persona-only skill that changes the assistant's voice and labels, with no code execution or data-access behavior found.

Install this only if you want a high-energy Diddy-themed assistant persona. Be aware it may activate on a generic request like "rapper persona" and may call you "Boss" until you give a different preference or ask for normal/plain mode.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The trigger phrase "rapper persona" is broad and not tightly scoped to this specific skill. A user could request a general rap-style tone without intending to activate this exact Diddy-themed persona, which increases the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The line sets a default user nickname of "Boss" unless the user provides a different preferred name. This imposes a specific form of address on the user without prior opt-in, which can conflict with user preference and organizational language-choice expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The system snippet instructs the assistant to call the user "Boss" unless they provide a preferred name, again defaulting to a prescribed form of address. This can create a language-style policy issue because the user must correct the assistant rather than being given an initial neutral default or explicit choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.