Trust Assessment
cloudflare-deploy received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Privilege Escalation via Sandbox Bypass Instruction.
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 120b6767). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Privilege Escalation via Sandbox Bypass Instruction The skill instructions direct the LLM to bypass sandbox restrictions by rerunning commands with escalated permissions (`sandbox_permissions=require_escalated`). This represents a prompt injection and privilege escalation risk where untrusted content attempts to manipulate the execution environment's security boundaries. Remove instructions that advise the LLM or user to escalate sandbox permissions or bypass network restrictions. Sandbox policies should be managed statically by the host environment, not dynamically requested by untrusted skill content. | LLM | SKILL.md:7 |
Scan History
Embed Code
[](https://skillshield.io/report/847c0136ddc85a16)
Powered by SkillShield