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 Agent instructed to use '--yolo' flag, bypassing sandbox and approvals.
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 | Agent instructed to use '--yolo' flag, bypassing sandbox and approvals The skill explicitly instructs the use of the `codex` CLI with the `--yolo` flag in multiple instances (e.g., lines 36 and 140). The skill itself documents `--yolo` as 'NO sandbox, NO approvals (fastest, most dangerous)' and a 'shortcut for --dangerously-bypass-approvals-and-sandbox'. This flag disables critical security mechanisms, allowing the agent to execute arbitrary commands with the user's permissions without any sandboxing or approval prompts. If the prompt provided to `codex` is derived from untrusted input, this creates a direct and severe command injection vulnerability, potentially leading to arbitrary code execution, data exfiltration, or system compromise. Avoid using the `--yolo` flag in production or automated contexts. If `--yolo` is absolutely necessary for specific development scenarios, ensure that all prompts passed to `codex` are strictly controlled, hardcoded, and never derived from untrusted user input. Implement robust input sanitization and validation if user input must be used. Prefer `--full-auto` or interactive modes with approvals. | LLM | SKILL.md:36 |
Scan History
Embed Code
[](https://skillshield.io/report/49261ae45231d53a)
Powered by SkillShield