The Agent Skills Directory

[SAFE]: The skill provides explicit defensive instructions to the agent, directing it to treat external code, XML files, and SQL logs as untrusted data and to ignore any embedded instructions that might attempt to override agent behavior or trigger command execution.
[SAFE]: Guidance on parameter binding correctly distinguishes between safe prepared statements and potentially dangerous raw SQL interpolation, strongly advising the use of closed allowlists for any dynamic SQL fragments.
[SAFE]: Security best practices for authorization and multi-tenancy are emphasized, specifically advising that sensitive identifiers like tenant ID or actor identity must be derived from authenticated server-side context rather than untrusted request parameters.

mybatis-patterns