The Agent Skills Directory

[SAFE]: The skill provides standard implementation patterns for the Convex platform. It correctly identifies security best practices, such as restricting cron jobs to internal-only functions and using environment variables for sensitive API keys.
[INDIRECT_PROMPT_INJECTION]: The skill demonstrates how to fetch data from external APIs (e.g., api.example.com). While standard for such integrations, developers should ensure that data from these ingestion points is validated. Evidence: 1. Ingestion points: syncExternalData function in convex/sync.ts fetches external API data. 2. Boundary markers: None present in the example code. 3. Capability inventory: ctx.db (database write), ctx.storage (storage delete), and fetch (network access) in convex/tasks.ts and convex/sync.ts. 4. Sanitization: Not explicitly shown in the provided code snippets.

convex-cron-jobs