The Agent Skills Directory

[SAFE]: The skill includes explicit instructions to protect sensitive information, advising users to provide query parameters "without disclosing sensitive data" and recommending the use of sanitized or representative data for benchmarking.
[SAFE]: Extensive safety documentation is provided regarding the use of EXPLAIN ANALYZE. The skill correctly warns that this command executes the underlying statement and that side effects (like sequence increments or external function calls) may not be undone by a rollback.
[SAFE]: All external references point to official documentation for PostgreSQL (postgresql.org) and SQLite (sqlite.org). These are well-known, trusted technical sources.
[SAFE]: No obfuscation, malicious persistence mechanisms, or unauthorized network operations were detected. The skill maintains a professional and technical focus on database optimization.
[INDIRECT_PROMPT_INJECTION]: The skill naturally processes untrusted data such as user-provided SQL and schema definitions. However, it mitigates risks by instructing the agent to work within bounded investigations, use representative fixtures, and verify all changes against semantic correctness and performance baselines. The overall risk is low and inherent to the skill's primary purpose.

sql-performance