Security Audit

jimliu/baoyu-skills:skills/baoyu-format-markdown

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-format-markdown 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 4 findings: 0 critical, 1 high, 3 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Unpinned npm dependency version, Command Injection via unescaped argument in spawnSync on Windows.

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

93%

LLM Behavioral Safety

78%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

3 findings

Dynamic Code

2 findings

Excessive Permissions

1 finding

Security Findings4

Severity	Finding	Layer	Location
HIGH	Command Injection via unescaped argument in spawnSync on Windows In `scripts/autocorrect.ts`, the `applyAutocorrect` function executes `npx.cmd` on Windows using `spawnSync` with the user-provided `filePath` as an argument. On Windows, spawning `.cmd` or `.bat` files implicitly invokes `cmd.exe` for command-line parsing. If the `filePath` contains shell metacharacters (such as `&`, `\|`, or `^`), they can be interpreted by `cmd.exe`, leading to arbitrary command execution. Sanitize the `filePath` to ensure it only contains valid alphanumeric characters, dots, and path separators, or avoid spawning `.cmd` files directly with untrusted arguments on Windows.	LLM	scripts/autocorrect.ts:8
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-format-markdown/SKILL.md:35
MEDIUM	Unpinned npm dependency version Dependency 'remark-cjk-friendly' is not pinned to an exact version ('^1.1.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk.	Dependencies	skills/baoyu-format-markdown/scripts/package.json
MEDIUM	Unpinned dynamic package execution via npx The script `scripts/autocorrect.ts` executes `npx autocorrect-node` to run autocorrect. However, `autocorrect-node` is not listed as a dependency in `package.json` or pinned to a specific version. This causes `npx` to dynamically fetch the latest version from the npm registry at runtime, exposing the environment to supply chain attacks (e.g., package hijacking or malicious updates). Add `autocorrect-node` to the `dependencies` or `devDependencies` in `package.json` with a pinned version, and run it via `npx --no-install` or directly via `bun x` / local node_modules binary path.	LLM	scripts/autocorrect.ts:8

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/9ce0ffa50d63d48d.svg)](https://skillshield.io/report/9ce0ffa50d63d48d)