The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): No instructions found attempting to bypass safety filters or override agent behavior.
[CREDENTIALS_UNSAFE] (SAFE): Database configurations correctly use environment variable placeholders (${DB_USER}, ${DB_PASS}) rather than hardcoded secrets.
[DATA_EXFILTRATION] (SAFE): No unauthorized network operations or access to sensitive system files (e.g., SSH keys, AWS creds) detected.
[COMMAND_EXECUTION] (SAFE): While the Bash tool is permitted, it is aligned with the skill's purpose of managing migrations and database tools. No malicious shell commands are present in the documentation.
[EXTERNAL_DOWNLOADS] (SAFE): Mentions standard, trusted libraries (Spring Boot, Liquibase, Hibernate) without suspicious remote execution patterns.

data-management