Trust Assessment
Mersal 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, 0 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Unpinned npm dependency version, Command Injection via child_process.exec.
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 14, 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 Python dynamic code execution (exec/eval/compile) 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/maherucifer/mersal-orem/index.js:13 | |
| 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/maherucifer/mersal-orem/index.js:2 | |
| CRITICAL | Command Injection via child_process.exec The `runEgoFilter` function in `index.js` uses `child_process.exec` to execute a Python script. The `text` argument, which is likely derived from untrusted input (e.g., user messages, LLM output), is directly interpolated into the shell command string without proper sanitization or escaping. This allows an attacker to inject arbitrary shell commands by crafting malicious input for the `text` variable, leading to arbitrary code execution on the host system. Replace `child_process.exec` with `child_process.execFile` or `child_process.spawn`, passing the input `text` as a separate argument in an array, rather than embedding it directly into the command string. Alternatively, if `exec` must be used, implement robust input sanitization and shell escaping for the `text` variable to neutralize any shell metacharacters. | LLM | index.js:15 | |
| MEDIUM | Unpinned npm dependency version Dependency 'clawdhub' is not pinned to an exact version ('^0.3.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/maherucifer/mersal-orem/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/f8c187b67e2425f1)
Powered by SkillShield