Trust Assessment
codex received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Shell Command Injection via Unsanitized User Prompt.
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 August 1, 2026 (commit a4d31ad1). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Shell Command Injection via Unsanitized User Prompt The instructions direct the LLM to construct shell commands by interpolating untrusted user prompts directly into a double-quoted string within a shell pipeline (e.g., `echo "your prompt here" | codex exec ...`). If a user provides a prompt containing shell metacharacters (such as double quotes, semicolons, or command substitution), it will lead to arbitrary command execution on the host system. Avoid passing user prompts directly via shell command interpolation. Instead, write the prompt to a temporary file and redirect stdin (e.g., `codex exec ... < prompt.txt`), or use safe process execution APIs that bypass the shell entirely. | LLM | SKILL.md:14 |
Scan History
Embed Code
[](https://skillshield.io/report/49b1f24d0022639b)
Powered by SkillShield