Back to skill

Security audit

Creative Prompts Arsenal

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a simple local creative prompt generator with no evidence of hidden access, persistence, networking, or destructive behavior.

This skill is appropriate for creative ideation tasks. It runs local prompt-generation logic and does not appear to request sensitive access, but users should still review generated prompts before applying them in sensitive professional, medical, legal, or high-stakes contexts.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · handler.py (reported line 131)May include surrounding context.

python
raw_material = frame['raw_material']
    return {
        'Expand': [
            f'List 10 possible angles for {context} without judging them yet.',
            f'What would make this {artifact} 20% more vivid, useful, or surprising for the {audience}?',
        ],
        'Invert': [