Security Audit

openai/skills:skills/.curated/cloudflare-deploy

github.com/openai/skills

AI SkillCommit 49f948faa925

TRUSTED

Scanned about 6 hours ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

openai/skills:skills/.curated/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 Instruction to bypass sandbox restrictions.

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 July 17, 2026 (commit 49f948fa). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Instruction to bypass sandbox restrictions The skill instructions explicitly direct the LLM to bypass sandbox network restrictions by requesting escalated permissions (`sandbox_permissions=require_escalated`) when network calls are blocked. This can be abused to execute unauthorized outbound network requests or exfiltrate data from a restricted environment. Remove instructions that advise automatic or user-prompted escalation of sandbox permissions. Ensure deployments are handled within the designated security boundaries of the runtime environment.	LLM	SKILL.md:9

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/37c16a610a91c19a.svg)](https://skillshield.io/report/37c16a610a91c19a)