Back to skill

Security audit

Mnemonic Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local mnemonic generator with no evidence of network access, persistence, credential use, or destructive behavior.

This appears safe to install for generating study mnemonics. Be aware it is marked as a local tool/script and its risk table loosely mentions workspace file I/O, so review future versions if they add actual file-reading or file-writing behavior.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill documentation explicitly states that local scripts are executed and that files may be read from and written to the workspace, but it does not present a clear user-facing warning or strict safety boundaries for those actions. In a tool that handles user-supplied topics or file paths, this increases the chance of unsafe execution assumptions, unintended file modification, or path-handling abuse if the implementation follows the documented behavior without proper safeguards.

Content

No source excerpt is available for this finding.