The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions to override safety protocols, bypass filters, or extract system prompts were detected in the instructional content.
[Data Exposure & Exfiltration] (SAFE): The skill does not contain hardcoded credentials, access sensitive file paths, or perform any network operations.
[Unverifiable Dependencies & RCE] (SAFE): No package managers (npm, pip, etc.) or remote script download patterns (curl|bash) are present.
[Indirect Prompt Injection] (INFO): The skill provides conceptual guidance on handling external data (RAG) but does not include any implementation code or active data ingestion points that create a vulnerability surface.
[No Code] (INFO): This skill is entirely comprised of markdown documentation and architectural patterns; it lacks any executable scripts, tool definitions, or configuration files that interact with the system host.

rag-engineer