Security Audit

jimliu/baoyu-skills:.claude/skills/release-skills

github.com/jimliu/baoyu-skills

AI SkillCommit 6b7a2e417500

TRUSTED

Scanned 24 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

jimliu/baoyu-skills:.claude/skills/release-skills received a trust score of 76/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Command Injection via Untrusted Git Commit Messages, Arbitrary Code Execution via Untrusted Release Hooks.

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 August 6, 2026 (commit 6b7a2e41). 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

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Command Injection via Untrusted Git Commit Messages The skill instructs the LLM to extract PR numbers from git merge commit messages and execute `gh pr view <number>`. If a repository contains malicious commit messages (e.g., from a pull request or untrusted contributor), the extracted 'number' could contain shell metacharacters, leading to arbitrary command execution when executed in the shell. Validate that the extracted PR number is strictly a positive integer before passing it to the shell command, or use a safe execution environment/API that does not invoke a shell.	LLM	SKILL.md:149
HIGH	Arbitrary Code Execution via Untrusted Release Hooks The skill automatically executes hooks (`prepare_artifact`, `publish_artifact`) defined in `.releaserc.yml` within the repository root. If the repository is untrusted or contains a malicious contribution, an attacker can define arbitrary shell commands in these hooks, which the AI agent will execute during the release workflow. Require explicit user confirmation before executing any hooks defined in `.releaserc.yml`, displaying the exact commands to be run, or disable arbitrary hook execution by default.	LLM	SKILL.md:64

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/816d585e947f9cea.svg)](https://skillshield.io/report/816d585e947f9cea)