Trust Assessment
codex-monitor received a trust score of 41/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), User-controlled arguments passed directly to subprocess.run.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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/odrobnik/codex-monitor/codex_monitor.py:32 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'main'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/odrobnik/codex-monitor/codex_monitor.py:32 | |
| HIGH | User-controlled arguments passed directly to subprocess.run The `codex_monitor.py` script executes external commands using `subprocess.run`. The arguments passed to these commands (`argv[1:]` or `argv[2:]`) are taken directly from user input without validation or sanitization. While `subprocess.run` with a list of arguments prevents shell injection, it does not protect against argument injection into the target `swift run` command or the underlying Swift executables (`CodexMonitor-CLI`, `CodexMonitor-App`). An attacker could potentially craft malicious arguments to exploit vulnerabilities in `swift run` or the Swift applications, leading to unintended operations, data exfiltration, or arbitrary code execution. The `SKILL.md` explicitly states "this wrapper passes through extra args," confirming the direct passthrough of untrusted input. Implement strict argument validation and sanitization for all user-provided inputs before passing them to `subprocess.run`. Only allow a predefined set of safe arguments and values. Avoid passing raw user input directly to external commands. If the Swift executables are designed to be controlled by the LLM, consider creating a more constrained API for them rather than a direct argument passthrough. | LLM | codex_monitor.py:33 |
Scan History
Embed Code
[](https://skillshield.io/report/6de3dfc9280678df)
Powered by SkillShield