Back to skill

Security audit

Gifts

Security checks for vulnerabilities and agentic risk

Overview

This skill keeps a local gift notebook and has privacy considerations, but its behavior is disclosed and matches its stated purpose.

Install only if you are comfortable keeping gift notes and personal details in local files under ~/gifts/. Avoid storing highly sensitive information about yourself or others, especially on shared devices or folders synced to cloud backups, and review notes before relying on them for gift decisions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases are very broad and map to common conversational behavior, which can cause the skill to activate when the user did not explicitly intend to store or retrieve gift-related personal data. In this skill, unintended activation is more dangerous because it leads directly to creating or updating local files containing sensitive personal information about named individuals, preferences, sizes, and history.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill encourages persistent storage of personal data in local markdown files, including birthdays, interests, clothing sizes, gift history, and a personal wishlist, but provides no warning or consent guidance. This is risky because users may unknowingly store sensitive or intimate data about themselves and others without understanding retention, exposure on shared machines, backups, or local compromise.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- After giving: log reaction

## What NOT To Do
- Suggest generic gifts without checking their file
- Forget to log gifts (prevents repeats)
- Miss capturing "I want that" moments
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.