Trust Assessment
green-tea-persona 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 9 findings: 5 critical, 0 high, 2 medium, and 1 low severity. Key findings include Arbitrary command execution, Missing required field: name, Unpinned npm dependency version.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
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 Findings9
| 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/autogame-17/green-tea-persona/speak.js:3 | |
| 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/autogame-17/green-tea-persona/speak.js:58 | |
| 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/autogame-17/green-tea-persona/speak.js:68 | |
| 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/autogame-17/green-tea-persona/speak.js:99 | |
| CRITICAL | Command Injection via unsanitized target ID in execSync The `speak.js` script constructs a shell command using `child_process.execSync` and includes the user-provided `--target` option directly within double quotes. While quoted, a malicious user can craft the `target` value to break out of the quotes and inject arbitrary shell commands. For example, providing `--target 'id"; rm -rf / #'` could lead to arbitrary code execution on the host system. The `options.target` variable must be properly escaped for shell execution before being included in the `cmd` string. A safer approach would be to pass arguments as an array to `child_process.spawn` or `child_process.execFile` instead of constructing a single command string. If `execSync` must be used with a string, ensure `options.target` is escaped using a robust shell escaping function. | LLM | speak.js:85 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/autogame-17/green-tea-persona/SKILL.md:1 | |
| MEDIUM | Unpinned npm dependency version Dependency 'commander' is not pinned to an exact version ('^11.0.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/autogame-17/green-tea-persona/package.json | |
| 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/autogame-17/green-tea-persona/package.json | |
| INFO | Unpinned dependencies in package.json The `package.json` file specifies dependencies (`commander`, `dotenv`) using caret (`^`) ranges, allowing for minor and patch updates. While `package-lock.json` pins exact versions, relying on caret ranges in `package.json` can introduce supply chain risks if the lockfile is not consistently used or if a malicious update is published within the allowed range and the lockfile is regenerated. This is a common practice but represents a potential, albeit mitigated, risk. Consider using exact version pinning in `package.json` (e.g., `commander: "11.1.0"`) or regularly auditing dependencies for known vulnerabilities. Ensure `package-lock.json` is always committed and used during deployment to guarantee consistent dependency versions. | LLM | package.json:10 |
Scan History
Embed Code
[](https://skillshield.io/report/d95abd9ab2f385ee)
Powered by SkillShield