The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions designed to override agent behavior or bypass safety guardrails were identified. The tone is purely instructional.- [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, sensitive local file path access, or exfiltration patterns were detected.- [Obfuscation] (SAFE): No Base64, zero-width characters, or other encoding techniques were found.- [External Downloads] (SAFE): The skill references official Cloudflare documentation URLs for retrieval, which is standard practice for this use case.- [Remote Code Execution] (SAFE): There is no evidence of remote script execution (e.g., curl | bash) or dynamic code execution on untrusted data.

durable-objects