Security audit

pattern-lock-tutor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local command-line trainer whose file storage is disclosed and aligned with its purpose, but users should not store real unlock patterns or PINs in it.

Use this only with training sequences or look-alike patterns, not real unlock patterns, PINs, safe combinations, or account secrets. Expect a pattern_tutor.json file to be created in whatever directory you run it from, and delete that file when you are done if the practice data is sensitive.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 84% confidence
Finding: The skill describes persistent local storage (pattern_tutor.json in the current working directory) and command execution that implies file read/write behavior, but it does not declare any explicit tool scope or permissions. Undeclared file access weakens least-privilege guarantees and can surprise a host system into granting broader filesystem capabilities than reviewers or users expect, especially in a skill that handles potentially sensitive motor-sequence data such as lock patterns or PIN-like sequences.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.