Security Audit

systems-programming-rust-project

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

TRUSTED

Scanned about 6 hours ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

systems-programming-rust-project received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via unsanitized user input in generated shell commands.

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 February 20, 2026 (commit e36d6fd3). 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

85%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via unsanitized user input in generated shell commands The skill instructs the LLM to generate shell commands, such as `cargo new project-name` and `echo ... >> .gitignore`, based on user requirements provided via `$ARGUMENTS`. If the LLM directly interpolates unsanitized user input (e.g., for `project-name`) into these commands and executes them, or provides them for user execution without proper warnings, it could lead to command injection. An attacker could craft malicious input (e.g., `my_project; rm -rf /`) to execute arbitrary commands on the system where the LLM's generated code is run or where the LLM itself executes commands. Ensure all user-provided input used in shell commands is strictly validated and sanitized (e.g., whitelisting allowed characters, escaping shell metacharacters) before being passed to `cargo` or other shell utilities. If the LLM executes commands, ensure it runs in a highly restricted sandbox. If the LLM only generates commands for the user, clearly warn the user about the risks of executing untrusted input.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/3176d50339bc8c28.svg)](https://skillshield.io/report/3176d50339bc8c28)