Back to skill

Security audit

Learned from AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward note-making workflow that saves AI chat summaries and cheat sheets into a local notes folder, with no evidence of hidden execution, credential use, exfiltration, or destructive behavior.

Install this if you want AI conversations converted into local study notes. Before use, know that it normally creates files under notes/ and uses a subagent by default; ask for a preview, a different folder, or no file writes if you want tighter control.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to always save outputs into notes/ by default, which can cause filesystem modifications without first making that behavior explicit to the user at execution time. In agent environments with tool access, silent default writes can create unexpected files, overwrite adjacent knowledge artifacts if naming is imperfect, and normalize state-changing behavior without consent or confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The workflow repeatedly directs the agent to write a main note and cheat sheet into notes/, reinforcing automatic filesystem changes as the normal path without any safety notice or consent step. Because the skill is specifically designed to transform user input into persisted artifacts, the repeated write instructions increase the chance of unintended file creation, clutter, or accidental modification of durable notes.

Content

No source excerpt is available for this finding.