The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): No instructions found that attempt to bypass safety filters, extract system prompts, or override agent behavior. The instructions are strictly focused on database engineering.
[DATA_EXFILTRATION] (SAFE): No hardcoded credentials or unauthorized network calls detected. The skill specifically recommends Row Level Security (RLS) as a best practice for data safety.
[COMMAND_EXECUTION] (SAFE): The skill utilizes the run_command tool for standard database operations such as prisma migrate and npm run seed. These operations are consistent with the stated purpose of a database architect.
[REMOTE_CODE_EXECUTION] (SAFE): No remote scripts are downloaded or executed. Dependencies mentioned (Prisma) are standard tools for the domain.
[INDIRECT_PROMPT_INJECTION] (LOW): While the skill ingests SQL and schema files which could theoretically contain malicious instructions, its primary purpose is structural design and validation, and it contains no patterns of high-risk interpolation or lack of boundary management in the provided files.

resonance-database