Security Audit

jimliu/baoyu-skills:skills/baoyu-xhs-images

github.com/jimliu/baoyu-skills

AI SkillCommit 6b7a2e417500

CAUTION

Scanned 24 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

jimliu/baoyu-skills:skills/baoyu-xhs-images received a trust score of 67/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 3 findings: 0 critical, 2 high, 1 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Out-of-workspace filesystem access via EXTEND.md configuration paths, Execution of untrusted bundled wrappers and external CLI 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 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

93%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

2 findings

Excessive Permissions

2 findings

Security Findings3

Severity	Finding	Layer	Location
HIGH	Out-of-workspace filesystem access via EXTEND.md configuration paths The skill instructions direct the LLM to read and write configuration files (EXTEND.md) outside the project workspace, specifically targeting the user's home directory ($HOME/.baoyu-skills/...) and XDG config directory ($HOME/.config/...). This breaks workspace isolation and allows the skill to potentially access or overwrite sensitive files in the user's home directory. Restrict all configuration and state files to the local project workspace (e.g., .baoyu-skills/ within the current repository) and do not attempt to access the user's home directory or global XDG directories.	LLM	SKILL.md:240
HIGH	Execution of untrusted bundled wrappers and external CLI commands The skill instructs the LLM to execute external CLI commands (baoyu-image-gen) or 'invoke the bundled wrapper directly' if the CLI is unavailable. Executing bundled wrappers or binaries from an untrusted repository can lead to arbitrary code execution on the user's machine. Avoid executing bundled wrappers or external CLI binaries directly. Instead, rely on secure, sandboxed APIs or official, verified package dependencies.	LLM	SKILL.md:30
MEDIUM	Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated.	Static	skills/baoyu-xhs-images/SKILL.md:309

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/170e7826c8769720.svg)](https://skillshield.io/report/170e7826c8769720)