Security audit

工作报告PPT生成技能

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese work-report PPT generator that writes a user-requested presentation file and does not show hidden, destructive, persistent, or data-exfiltrating behavior.

Install this if you want a Chinese-language work-report PPT generator. Be aware that it defaults to saving under ~/Documents and uses fixed Chinese formatting/text unless you provide a different output path or modify the script.

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 (4)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The invocation examples are broad natural-language phrases such as '帮我生成一份本周工作汇报PPT' and '创建一个项目进度汇报', which can plausibly overlap with ordinary user requests. In an agent environment, this increases the chance of unintended skill auto-selection or over-triggering, causing the system to invoke local file-writing behavior when the user may have only been asking for drafting help or general advice.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: This code uses fixed Chinese text in the default filename, CLI description/help, and slide content, which imposes a specific language/locale by default. The policy explicitly flags language or locale constraints when they are forced without user opt-in or a documented justification.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The generated presentation always ends with Chinese-language text regardless of user preference. This is a natural-language policy issue because the skill enforces a single language rather than offering a choice or documenting a justified locale restriction.

Natural-Language Policy Violations

Low

Confidence: 79% confidence
Finding: The description requires the first page title to use 宋体, which reflects a specific locale formatting choice, but the document does not mention any user opt-in or region-specific justification. This can be a natural-language policy issue when the skill appears to enforce a locale-specific presentation style by default.

Static analysis

No suspicious patterns detected.