Trust Assessment
apple-docs received a trust score of 72/100, 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, 1 high, 2 medium, and 0 low severity. Key findings include Unsafe deserialization / dynamic eval, Unpinned third-party data source for WWDC content.
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 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned third-party data source for WWDC content The skill fetches WWDC video data (JSON files) directly from the `main` branch of a third-party GitHub repository (`raw.githubusercontent.com/kimsungwhee/apple-docs-mcp/main/data/wwdc/`). This introduces a supply chain risk as the content of the `main` branch can change at any time without explicit versioning. A compromise of the `kimsungwhee/apple-docs-mcp` repository or an unreviewed change to its `main` branch could lead to the skill fetching malicious or unexpected data. While the current usage appears to be for displaying information, manipulated data could lead to incorrect responses, or if the skill's parsing logic had vulnerabilities, it could be exploited. The `SKILL.md` description stating 'WWDC videos bundled offline' contradicts this live fetching, indicating a potential misunderstanding or outdated documentation. 1. Pin the `WWDC_DATA` URLs to a specific commit hash or release tag of the `apple-docs-mcp` repository instead of the mutable `main` branch. 2. Alternatively, if the data is truly meant to be 'bundled offline' as stated in `SKILL.md`, ensure these files are included in the skill package and loaded from local paths, removing the external dependency. 3. Implement content integrity checks (e.g., checksums) if fetching from external sources is unavoidable. | LLM | cli.js:27 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/thesethrose/apple-docs/cli.js:225 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/thesethrose/apple-docs/cli.js:239 |
Scan History
Embed Code
[](https://skillshield.io/report/0baf90aabfb99056)
Powered by SkillShield