Security Audit
jimliu/baoyu-skills:skills/baoyu-post-to-weibo
github.com/jimliu/baoyu-skillsTrust Assessment
jimliu/baoyu-skills:skills/baoyu-post-to-weibo received a trust score of 71/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 5 findings: 0 critical, 0 high, 4 medium, and 1 low severity. Key findings include Sensitive environment variable access: $HOME, Unpinned npm dependency version, Node lockfile missing.
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
Behavioral Risk Signals
Security Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| 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-post-to-weibo/SKILL.md:31 | |
| MEDIUM | Unpinned npm dependency version Dependency 'baoyu-chrome-cdp' is not pinned to an exact version ('^0.1.1'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/baoyu-post-to-weibo/scripts/package.json | |
| MEDIUM | Insecure Temporary File Creation The script writes HTML content to a predictable file path in the shared temporary directory ('/tmp/weibo-article-content.html' on Unix-like systems). A local attacker could pre-create a symlink at this path pointing to a sensitive file owned by the victim, causing the script to overwrite it (Symlink/Temp File Hijacking). Use a unique temporary file path by utilizing 'fs.mkdtemp' or a library like 'tmp' to generate a secure, random filename within the temporary directory. | LLM | scripts/weibo-article.ts:53 | |
| MEDIUM | AppleScript Injection via targetApp Parameter The 'targetApp' parameter is interpolated directly into an AppleScript string without sanitization or escaping. If an attacker can influence the '--app' command-line argument, they can execute arbitrary AppleScript commands on macOS. Sanitize the 'targetApp' input to ensure it only contains alphanumeric characters and spaces, or escape double quotes and backslashes before interpolating it into the AppleScript string. | LLM | scripts/paste-from-clipboard.ts:41 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/baoyu-post-to-weibo/scripts/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/9099b7ccb1f036b0)
Powered by SkillShield