The Agent Skills Directory

[SAFE]: The skill consists of prompt-based instructions for PostgreSQL database analysis. No executable scripts, system-level commands, or external remote code sources are present.
[SAFE]: No patterns associated with data exfiltration, credential theft, or unauthorized network access were detected.
[INDIRECT_PROMPT_INJECTION]: The skill instructions involve analyzing user-provided database schemas and queries, which constitutes an ingestion point for untrusted data. However, the skill does not define any tool use or execution capabilities, significantly limiting the impact of any potential injection. Ingestion points: Database query patterns and schema shapes described in SKILL.md. Boundary markers: None. Capability inventory: None. Sanitization: None.

postgres-pro