Trust Assessment
skill-compatibility-checker 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 12 findings: 6 critical, 1 high, 4 medium, and 1 low severity. Key findings include Unsafe environment variable passthrough, Arbitrary command execution, Credential harvesting.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings12
| 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/snail3d/clawforgod/skill-compatibility-checker-skill/scripts/checker.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/snail3d/clawforgod/skill-compatibility-checker-skill/scripts/checker.js:117 | |
| 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/snail3d/clawforgod/skill-compatibility-checker-skill/scripts/checker.js:119 | |
| 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/snail3d/clawforgod/skill-compatibility-checker-skill/scripts/checker.js:471 | |
| CRITICAL | Credential harvesting Bulk environment variable dump Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/snail3d/clawforgod/skill-compatibility-checker-skill/scripts/checker.js:176 | |
| CRITICAL | Command Injection via unsanitized external input The `commandExists` function, used to verify the presence of CLI tools, directly executes shell commands (`which` or `where`) using `child_process.execSync`. The `cmd` argument to `commandExists` is derived from untrusted sources: the `bin` field in an analyzed skill's `package.json` (in `checkBinConflicts`) and CLI tool mentions in an analyzed skill's `SKILL.md` content (in `checkDependencies`). A malicious skill could inject arbitrary shell commands into these fields, leading to remote code execution on the system running the checker. Replace `child_process.execSync` with a safer method for checking command existence. For example, use `child_process.spawnSync` with `command -v` or `type` and pass the command name as a separate argument to prevent shell interpretation. Alternatively, implement strict whitelisting for allowed CLI tool names before attempting execution. | LLM | scripts/checker.js:109 | |
| HIGH | Unsafe environment variable passthrough Bulk environment variable harvesting Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/snail3d/clawforgod/skill-compatibility-checker-skill/scripts/checker.js:176 | |
| 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/snail3d/clawforgod/skill-compatibility-checker-skill/scripts/checker.js:177 | |
| 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/snail3d/clawforgod/skill-compatibility-checker-skill/scripts/checker.js:283 | |
| 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/snail3d/clawforgod/skill-compatibility-checker-skill/scripts/checker.js:309 | |
| MEDIUM | Supply Chain Risk: Execution of external security scanner skill The `runSecurityScan` function invokes an external program, `security-scanner-skill`, to perform security analysis using `child_process.spawnSync`. While `spawnSync` is generally safer for argument handling than `execSync`, this introduces a supply chain risk. The security of this skill becomes dependent on the trustworthiness and integrity of the `security-scanner-skill`. If `security-scanner-skill` is compromised or malicious, it could be used to execute arbitrary code or exfiltrate data, effectively bypassing the checks of this skill. To mitigate this supply chain risk, consider implementing security scanning capabilities directly within this skill, or ensure that `security-scanner-skill` is cryptographically signed and its integrity verified before execution. Provide clear warnings to users about the trust implications of running external security tools and offer guidance on how to verify their authenticity. | LLM | scripts/checker.js:260 | |
| 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/snail3d/clawforgod/skill-compatibility-checker-skill/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/489d8443aabee796)
Powered by SkillShield