Back to skill

Security audit

class-ppt-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a classroom PPT helper with no executable code or hidden privileges, though its language defaults and one reference link are rough edges.

Before installing, treat this as a narrow helper for Chinese junior-high class meeting and English lesson PPT creation. Review the generated lesson content for accuracy, age appropriateness, and preferred classroom language, and be aware that one reference link in the skill appears mistyped.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions are broad enough that the skill may activate on vague mentions of '班会' or '英语课' together with PPT, even when the user did not clearly request this specific workflow. Overbroad activation can cause incorrect tool routing, unintended retrieval/generation behavior, and increased exposure to prompt-scope confusion if competing skills or user intents are present.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill hard-codes output language by lesson type ('全中文' for class meetings and '中英混合' for English lessons) without checking the user's stated language preference. This can override user intent, produce inappropriate outputs for the audience, and create reliability and usability issues, though it is not a direct code-execution or data-exfiltration risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The markdown content is entirely written as a Chinese-only framework and examples, with no indication that users may choose another language or that the skill is limited to a Chinese-language or region-specific context. This creates a natural-language locale constraint that can conflict with organizational language-choice policies.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file contains a topic title in English ('The Power of Yet') within an otherwise Chinese-language document, with no indication that users can choose their preferred language or locale. The stated policy category covers language or locale constraints in natural-language content, and this mixed-language presentation may be inconsistent with a user's expected language setting.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

Line L44 states '语言:英语为主,中文仅解释难点', which imposes a language policy rather than offering a user-selectable preference. Under the stated policy criteria, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.