Back to skill

Security audit

Yys Wallpaper

Security checks for vulnerabilities and agentic risk

Overview

This wallpaper downloader mostly does what it says, but its filesystem handling is broader than advertised and should be reviewed before installation.

Install only if you are comfortable with a script that downloads many images from the internet and writes them under your home directory. Use only the documented resolution values, avoid --no-skip unless you trust the destination directory contents, and check whether files are saved under ~/Pictures rather than the Chinese path shown in the description.

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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/download.py:112
Finding

Unvalidated Resolution Allows Directory Creation Outside the Intended Save Location

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/download.py:69
Finding

Symlink Following Can Overwrite User-Writable Files During Downloads

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The metadata says files are saved under ~/图片/{分辨率}/, while the body later states ~/Pictures/{分辨率}/. This inconsistency can mislead users about where data will be written, reducing transparency and potentially causing unintended storage use or difficulty auditing what the skill changed.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill performs network access and filesystem reads/writes but does not declare any tool scope or permissions boundary. In an agent environment, missing explicit capability declarations can cause users or orchestrators to invoke a skill without understanding that it will download remote content and write large amounts of data locally.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger conditions include broad intents like wanting to 'organize wallpapers' or 'batch download images', which could cause the skill to be selected in contexts where the user did not specifically ask to fetch large volumes of content from this site. Over-broad routing increases the chance of unexpected network activity and disk writes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Although the document mentions image counts and sizes later, it lacks a prominent upfront warning that execution will perform large-scale network downloads and write potentially gigabytes of data to the local filesystem. In agent use, insufficient disclosure can lead to surprising resource consumption, bandwidth usage, and storage exhaustion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring and CLI descriptions are entirely in Chinese, and the script does not offer any language or locale selection. This creates a natural-language policy concern because it imposes a specific language on all users without opt-in or documented justification.

Content

No source excerpt is available for this finding.