The Agent Skills Directory

[PROMPT_INJECTION]: The skill ingests SQL query strings from the pg_stat_statements extension to identify optimization targets. This constitutes a risk surface where the agent processes external data from the database environment.
Ingestion points: SQL query text retrieved from diagnostic queries in Step 1 (e.g., pg_stat_statements).
Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore embedded commands within the ingested query text.
Capability inventory: The skill performs codebase analysis and suggests structural code changes and Infrastructure as Code updates in neon.ts (Steps 2, 3, and Infrastructure section).
Sanitization: No specific sanitization or filtering is prescribed for the ingested diagnostic data.
[EXTERNAL_DOWNLOADS]: The skill references and installs configuration utilities and additional skill modules from official project repositories and documentation domains.
Evidence: Fetches skill definitions from https://neon.com/docs/ai/skills/neon/SKILL.md and uses npm i @neon/config for infrastructure configuration.

neon-postgres-egress-optimizer