Back to skill

Security audit

Gift Idea Match Board

Security checks for vulnerabilities and agentic risk

Overview

This is a document-only gift-planning skill with clear privacy and no-shopping boundaries and no executable behavior.

Safe to install for ordinary gift planning. Users should still avoid entering full addresses, account details, exact private dates, medical or financial information, and should treat any budget field as a comfort range rather than financial advice.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The acceptance test explicitly requires English-only output, which creates an unjustified language restriction unrelated to the skill's privacy-light gift-planning purpose. While not a classic security exploit, this can cause exclusionary behavior, override user language preference, and encourage downstream prompt logic that rejects or mishandles non-English inputs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest sets "language": "en", which is a natural-language locale constraint. There is no nearby indication that users can opt into another language or that the English-only setting is required for a documented region-specific purpose.

Content

No source excerpt is available for this finding.