Trust Assessment
confirm-form received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 3 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, User data uploaded to public GitHub Gist, Arbitrary shell command execution via `execSync`.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.
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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Node.js child_process require Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/xiaozhuang0127/confirm-form/scripts/generate.js:16 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/xiaozhuang0127/confirm-form/scripts/generate.js:111 | |
| CRITICAL | User data uploaded to public GitHub Gist The `generate.js` script uploads the generated HTML form, which embeds the user-provided `questions.json` data, to a *public* GitHub Gist. This means any sensitive information present in the `questions.json` (e.g., project details, internal findings, recommendations) will be publicly accessible on the internet under the hardcoded `xiaozhuang0127` GitHub account. This poses a significant risk of data leakage and exposure of confidential information. Avoid uploading potentially sensitive user data to public platforms. Provide an option for private gists, or implement a secure, authenticated method for sharing. Explicitly warn users about public data exposure if public gists are the only option. Consider redacting sensitive fields before upload or using a different sharing mechanism. | LLM | scripts/generate.js:99 | |
| HIGH | Arbitrary shell command execution via `execSync` The script uses `child_process.execSync` to execute external commands (`gh gist create`). While the current usage appears to construct arguments safely from internally generated values (`outputFile`, `formId`), the presence of `execSync` grants the skill broad permissions to execute arbitrary shell commands. This increases the attack surface and could lead to command injection if future modifications or unforeseen interactions introduce user-controlled input into the command string. Replace `execSync` with a dedicated GitHub API client library for Gist creation to avoid shelling out. If shell execution is unavoidable, use `child_process.spawn` with an array of arguments to prevent shell interpretation, and ensure all arguments are strictly validated and sanitized. Minimize the scope of commands that can be executed. | LLM | scripts/generate.js:10 |
Scan History
Embed Code
[](https://skillshield.io/report/1fa1bb54659ded39)
Powered by SkillShield