Security Audit

Jamkris/everything-gemini-code:skills/frontend-slides

github.com/Jamkris/everything-gemini-code

AI SkillCommit 6c6f43aaa3d6

CRITICAL

Scanned 8 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

Jamkris/everything-gemini-code:skills/frontend-slides received a trust score of 43/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via Python Subprocess Execution, Potential Command Injection via OS-Specific File Openers.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on March 30, 2026 (commit 6c6f43aa). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Filesystem Write

2 findings

Shell Execution

2 findings

Dynamic Code

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via Python Subprocess Execution The skill explicitly instructs the AI to use `python3` with `python-pptx` for converting PowerPoint files. If the filename or path of the `.ppt` or `.pptx` file is derived from untrusted user input and not properly sanitized before being passed to a `python3` command, it could lead to command injection. An attacker could craft a malicious filename to execute arbitrary commands on the host system. When executing `python3` or any other system command, ensure that all arguments derived from user input (e.g., file paths, filenames) are strictly sanitized, quoted, and escaped. Prefer using subprocess APIs that accept a list of arguments rather than a single shell string to prevent shell injection. Implement robust input validation for all file-related user inputs.	LLM	SKILL.md:120
HIGH	Potential Command Injection via OS-Specific File Openers The skill instructs the AI to use OS-specific commands (`open`, `xdg-open`, `start`) to open the generated HTML presentation. If the filename (`file.html` or `[presentation-name].html`) is constructed using untrusted user input without proper sanitization, an attacker could inject malicious commands into the file path, leading to arbitrary code execution on the host system when the command is invoked. Before using `open`, `xdg-open`, `start`, or similar commands with filenames derived from user input, ensure the filename is thoroughly sanitized. Validate that the filename contains only allowed characters and does not include shell metacharacters. If possible, use platform-specific APIs for opening files that do not involve direct shell execution, or ensure arguments are passed as a list to prevent shell injection.	LLM	SKILL.md:110

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/bd539638272337e4.svg)](https://skillshield.io/report/bd539638272337e4)