Back to skill

Security audit

sn-ppt-dazzle

Security checks for vulnerabilities and agentic risk

Overview

This presentation skill needs review because its renderer disables browser safeguards while loading online scripts.

Have the renderer's certificate validation, CSP enforcement and Chromium sandboxing restored before using confidential slides. Prefer locally bundled fonts and libraries for offline use. All four bundled files were inspected, including the scanner's partial reference; prerequisite skills and live CDN responses remain outside this review.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/render_deck.py
Finding

TLS verification is disabled for executable CDN resources

Content
View full analysis

Impact

Injected JavaScript can read the rendered presentation's DOM, transmit its contents to an attacker-controlled endpoint, and alter the presentation or screenshots. Host-level code execution is not established.

Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (8)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 279)May include surrounding context.

md
rectional/Point 三类光,全 deck 共用一个常驻场景、每页一个相机机位、翻页时相机沿弧线 lerp 巡游(注视点必须同步插值)。完整范例见 `fancy-cookbook.md`「代码搭建 3D 场景」+「单一 3D 世界相机航点运镜」。骨架期就把场景与相机搭起来跑通,逐页只调机位与该页 HTML。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 285)May include surrounding context.

md
- `references/fancy-cookbook.md` —— 技法配方:入场动画 / 跨页过渡 / 全局背景 / 交互彩蛋,含核心代码模式与参数安全范围。阶段 0 选型时读。

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Mandatory Google Fonts loading lacks a disclosure about external network requests.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The skill mandates Google Fonts for Chinese content without informing users that rendering or opening the generated deck makes third-party network requests. Those requests expose connection metadata such as IP address and browser information, creating an avoidable privacy concern for potentially sensitive business, medical, or legal presentations; the supplied content does not establish that slide text is transmitted.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'Npx Npx'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'Npx Npx'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.