Trust Assessment
coding-agent 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 Explicit recommendation of '--yolo' flag bypasses all security sandboxing.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Explicit recommendation of '--yolo' flag bypasses all security sandboxing The skill explicitly recommends and demonstrates the use of the `codex --yolo` flag in multiple examples. The skill itself describes this flag as 'NO sandbox, NO approvals (fastest, most dangerous)' and a 'shortcut for --dangerously-bypass-approvals-and-sandbox'. This flag grants the `codex` agent excessive permissions, allowing it to execute arbitrary commands (Command Injection), access any file on the system (Data Exfiltration), and potentially harvest credentials without any restrictions or user approval. This completely negates the security benefits of the `workdir` mechanism and poses a severe risk if the agent is compromised or misbehaves. Remove all recommendations and examples using the `--yolo` flag. Emphasize the use of `--full-auto` or interactive approval processes. If `--yolo` is deemed absolutely necessary for specific, highly controlled scenarios, add strong warnings and explicit instructions on how to mitigate its risks (e.g., running in a highly isolated container, with minimal `workdir` scope, and no network access). | LLM | SKILL.md:36 |
Scan History
Embed Code
[](https://skillshield.io/report/63bfed8ea61755cd)
Powered by SkillShield