Trust Assessment
clawland received a trust score of 14/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 5 findings: 2 critical, 1 high, 2 medium, and 0 low severity. Key findings include Arbitrary command execution, Unsafe deserialization / dynamic eval, Unpinned npm dependencies in common.js.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 33/100, 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 Findings5
| 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/ice-coldbell/clawland/scripts/common.js:29 | |
| 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/ice-coldbell/clawland/scripts/common.js:30 | |
| HIGH | Unpinned npm dependencies in common.js The `ensureDeps` function in `scripts/common.js` installs several npm packages (`@coral-xyz/anchor`, `@solana/spl-token`, `bs58`, `tweetnacl`) without specifying exact versions. This allows `npm` to fetch the latest available version, which could introduce breaking changes, security vulnerabilities, or even malicious code if a package maintainer's account is compromised. For security-critical dependencies, exact version pinning (e.g., `package@1.2.3`) is strongly recommended to ensure deterministic and secure builds. Pin all npm dependencies to exact versions (e.g., `package@1.2.3`) instead of major versions or unpinned versions. Regularly audit and update these pinned versions to incorporate necessary security fixes. | LLM | scripts/common.js:36 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/ice-coldbell/clawland/scripts/autoplay.js:73 | |
| MEDIUM | Direct shell command execution via execSync The `ensureDeps` function in `scripts/common.js` uses `child_process.execSync` to execute shell commands (`npm init` and `npm install`). While the arguments to `npm install` are currently hardcoded and not directly derived from user input, the use of `execSync` grants the skill the capability to run arbitrary shell commands. This is an excessive permission and poses a command injection risk if the command or its arguments were ever to be derived from untrusted input in the future. It's generally safer to use Node.js APIs or more constrained child process methods where possible. Avoid using `child_process.execSync` for dependency management. Consider using a `package.json` with pinned dependencies and instructing the user to run `npm install` manually, or use a more secure, sandboxed method for dependency resolution if available within the OpenClaw ecosystem. If `execSync` is absolutely necessary, ensure all arguments are strictly controlled and never derived from user input. | LLM | scripts/common.js:36 |
Scan History
Embed Code
[](https://skillshield.io/report/379de219411c8b01)
Powered by SkillShield