Trust Assessment
youdotcom-cli received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Unpinned dependency installation recommended.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned dependency installation recommended The skill recommends installing the `@youdotcom-oss/api` package globally without specifying a version (`npm install -g @youdotcom-oss/api` or `bun add -g @youdotcom-oss/api`). This practice means that the latest available version will always be installed, which introduces a supply chain risk. If a malicious update to the package is published, an agent following these instructions could inadvertently install and execute compromised code. The `allowed-tools` also permit `bunx` and `npx` usage, which often fetch the latest version, reinforcing this risk. Specify a fixed version for installation (e.g., `npm install -g @youdotcom-oss/api@2.0.5`) or use a lockfile mechanism. For `bunx`/`npx`, consider using `bunx @youdotcom-oss/api@2.0.5` if possible, or ensure the agent is configured to verify package integrity. | LLM | SKILL.md:14 |
Scan History
Embed Code
[](https://skillshield.io/report/ff48cf279ceecf3b)
Powered by SkillShield