The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains purely instructional content related to database design and architectural decision-making. No patterns of prompt injection, role-play bypasses, or safety filter overrides were detected.
[DATA_EXFILTRATION]: No network operations, hardcoded credentials, or sensitive file path accesses were identified. The skill correctly advises against using production privacy data in development seeds, which is a security best practice.
[REMOTE_CODE_EXECUTION]: The skill does not perform any external package installations or remote script executions. It is a documentation-based skill providing guidance on ORM and migration tool selection.
[COMMAND_EXECUTION]: There are no shell commands, system calls, or subprocess executions defined in the skill body.
[OBFUSCATION]: The content is written in clear, plain text (Chinese). No Base64, zero-width characters, homoglyphs, or other obfuscation techniques were detected.
[INDIRECT_PROMPT_INJECTION]: The skill defines a static framework for data modeling decisions and does not ingest or process untrusted external data at runtime.
[DYNAMIC_CONTEXT_INJECTION]: No dynamic context injection patterns (e.g., shell command placeholders) were found in the skill metadata or body.

data-modeling