The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-supplied requirements to generate code for database operations. * Ingestion points: The skill processes user prompts for data modeling and function authoring requests as described in the examples in SKILL.md. * Boundary markers: No explicit instructions or delimiters are present to separate user input from the skill's generated code context. * Capability inventory: The skill provides instructions for performing database write, patch, and delete operations, and executing external actions across SKILL.md. * Sanitization: The skill mitigates risks by mandating strict v.* validators for all function arguments and return values, and requires identity checks via ctx.auth.

convex-core