Trust Assessment
gutcheck 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 8 findings: 3 critical, 1 high, 1 medium, and 2 low severity. Key findings include Arbitrary command execution, Unpinned npm dependency version, Node lockfile missing.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 10/100, indicating areas for improvement.
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 Findings8
| 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/allen566/gutcheck/publish_gutcheck.js:5 | |
| 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/allen566/gutcheck/publish_gutcheck.js:28 | |
| 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/allen566/gutcheck/publish_gutcheck.js:98 | |
| HIGH | Shell command execution with potentially untrusted path The `publish_gutcheck.js` script uses `child_process.execSync` to execute shell commands. Specifically, the `npx clawhub publish` command incorporates `tempDir`, which is derived from `process.cwd()`. If the current working directory (`process.cwd()`) can be controlled by an attacker to contain shell metacharacters (e.g., `my_skill; malicious_command;`), this could lead to arbitrary command execution on the host system. While `process.cwd()` is typically trusted in a controlled environment, this pattern is a known command injection vector if the execution context is compromised or influenced by untrusted input. To mitigate this risk, ensure that `tempDir` is properly sanitized or quoted for shell execution. A more robust solution would be to use `child_process.spawn` or `child_process.execFile` with an array of arguments, which prevents shell interpretation of individual path components. Alternatively, ensure the execution environment guarantees a trusted `process.cwd()`. | LLM | publish_gutcheck.js:98 | |
| MEDIUM | Unpinned npm dependency version Dependency 'express' is not pinned to an exact version ('^4.18.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/allen566/gutcheck/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/allen566/gutcheck/package.json | |
| LOW | Dependencies use caret ranges, allowing minor/patch updates The `package.json` file specifies dependencies using caret (`^`) version ranges (e.g., `^4.18.0` for `express`). This allows `npm` to automatically install newer minor or patch versions. While common, this practice introduces a supply chain risk as a new version of a dependency could potentially introduce vulnerabilities or malicious code without explicit review by the skill developer. This is often referred to as 'unpinned' or 'loosely pinned' dependencies. Pin dependencies to exact versions (e.g., `1.2.3`) or use tilde (`~`) ranges for patch updates only to ensure deterministic builds and reduce the risk of unexpected vulnerabilities from upstream changes. Regularly audit dependencies for known vulnerabilities. | LLM | package.json:19 | |
| INFO | Skill installation uses direct shell commands The skill's manifest defines installation steps using `kind: "shell"`, which directly executes shell commands (`cd gutcheck && npm install`). While the commands themselves are hardcoded and appear benign in this context, the use of direct shell execution is a powerful primitive. If the command string were ever constructed from untrusted input, it would be a critical command injection vulnerability. In this specific case, the commands are fixed and do not appear to incorporate external untrusted data. Ensure all components of shell commands are strictly controlled and never derived from untrusted user input. If possible, prefer specific tool calls or API-based execution over generic shell commands when available, as they often provide better input sanitization and security guarantees. | LLM | SKILL.md |
Scan History
Embed Code
[](https://skillshield.io/report/182048281d630458)
Powered by SkillShield