Security audit

Greeting Card Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple greeting-card writing skill with no code execution, persistence, or data access, though its trigger wording and Chinese default may be broader than some users expect.

Installers should expect this skill to help compose greeting-card style messages. Users who prefer another language or tone should state that explicitly, since the skill defaults to warm Chinese when preferences are missing.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill description is broad enough to match general requests to 'write wishes' or 'compose messages,' which can cause the agent to invoke this skill for ordinary writing tasks outside the intended greeting-card scope. This can lead to inappropriate routing, reduced user control, and accidental overriding of a more suitable skill or core assistant behavior.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: The instruction says to default to "warm + Chinese" if the user has no preference, which imposes a specific language choice absent explicit user selection. This can violate language or locale preference policy because the user may expect a neutral default or to be asked first.

Static analysis

No suspicious patterns detected.