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 Input in Stdin Piping.
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 October 1, 2026 (commit 439cd3a9). 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 Input in Stdin Piping The skill instructions direct the LLM to resume sessions by piping the user's prompt into the `codex` command using `echo "your prompt here" | codex exec ...`. If the user's prompt contains shell metacharacters, command substitutions (such as `$(...)` or backticks), or variable expansions, they will be executed by the host shell. This allows arbitrary command execution on the user's system. Avoid using `echo "..." | command` to pass user input to a shell command. Instead, use a heredoc with a single-quoted delimiter to prevent shell expansion, such as: ```bash codex exec --skip-git-repo-check resume --last << 'EOF' [user prompt here] EOF ``` | LLM | SKILL.md:11 |
Scan History
Embed Code
[](https://skillshield.io/report/49b1f24d0022639b)
Powered by SkillShield