Trust Assessment
bundle-checker received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Potential Data Exfiltration to External LLM, Unpinned `npx` dependency.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Data Exfiltration to External LLM The skill describes an external tool (`ai-bundle-check`) that explicitly states it "Scans your package.json and build output, identifies heavy dependencies, and sends the analysis to GPT-4o-mini." This constitutes exfiltration of potentially sensitive local project data (e.g., internal package names, file paths, build configurations) to a third-party LLM service without explicit consent or clear data handling policies within the skill's description. An AI agent using this skill would be directed to use a tool with this behavior. Clearly state what data is collected, how it's anonymized/sanitized, and obtain explicit user consent before sending any local data to external services. Provide options to disable this feature or use a local LLM. | LLM | SKILL.md:63 | |
| HIGH | Unpinned `npx` dependency The skill instructs the execution of an external package via `npx ai-bundle-check`. Using `npx` without a specific version (e.g., `@1.2.3`) means the latest version of the package will always be fetched and executed. This introduces a supply chain risk, as a malicious update to the `ai-bundle-check` package or a typosquatted package could lead to arbitrary code execution on the host system. Pin the `npx` command to a specific, known-good version (e.g., `npx ai-bundle-check@1.2.3`) to ensure deterministic execution and mitigate risks from malicious updates. Consider adding a checksum verification if possible. | LLM | SKILL.md:12 |
Scan History
Embed Code
[](https://skillshield.io/report/5fb9891a7940f902)
Powered by SkillShield