Security audit

Finance Training Outline

Security checks for vulnerabilities and agentic risk

Overview

This is a simple finance-training outline helper with no code execution, data access, persistence, or hidden behavior.

Installation is reasonable for users who want finance training outline assistance. Be aware that broad trigger terms like course design or talent development may cause this skill to activate for general training requests; finance-specific triggers would make it cleaner.

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

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger keywords are broad, generic HR/L&D terms such as '培训大纲', '课程设计', '企业大学', and '人才培养', which can overlap with many normal user requests outside this skill’s narrow finance-training purpose. This can cause unintended invocation, routing users into the wrong skill, creating prompt/context confusion and increasing the chance of inappropriate outputs or policy bypass through misselection.

Static analysis

No suspicious patterns detected.