Back to skill

Security audit

my-notes-helper

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk notes/reference skill with an unnecessary but harmless greeting script and no evidence of persistence, credential access, network execution, or destructive behavior.

Before installing, understand that this skill appears to be a static collection of tips and links, not a real note-storage tool. The included script is unnecessary for the stated purpose, but the inspected version only prints a greeting.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The skill’s declared purpose is a notes helper, but the documented behavior includes executing a shell script and lacks any actual note-storage functionality. This kind of description-behavior mismatch can mislead users and reviewers about what the skill does, reducing scrutiny and making it easier for unexpected or unsafe behavior to be introduced later.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

Documentation for a simple notes helper instructs users to run a shell script, which is unnecessary for the stated purpose and expands the attack surface. Even if the current script is harmless, encouraging shell execution in a low-risk context conditions users to run commands they may not inspect, enabling abuse if the script changes or is replaced.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

Advertising an unrelated demo script inside a notes/reference helper is a trust and transparency issue because it introduces behavior outside the user’s reasonable expectations. While not inherently malicious, unrelated executable content in a passive-reference skill can conceal or normalize unnecessary execution paths.

Content

No source excerpt is available for this finding.