The Agent Skills Directory

[SAFE]: The skill demonstrates best practices for managing sensitive information, utilizing environment variables for the iGrant.io API key and ensuring it is restricted to server-side operations to prevent exposure to the client or browser.\n- [PROMPT_INJECTION]: The skill processes user-supplied profile data (name, email, phone) which is transmitted to the backend API. This represents a potential surface for indirect prompt injection if the stored data is later retrieved and processed by an AI agent without adequate validation. Ingestion points were identified in references/src/server.ts, with data flow to the network capabilities in references/src/consentClient.ts.\n- [EXTERNAL_DOWNLOADS]: The references/package.json file lists several Node.js dependencies with version numbers that do not currently exist in the public registry (e.g., express@4.22.2, typescript@5.9.3). These versions appear to be placeholders aligned with the skill's future-dated metadata (July 2026) and do not show signs of malicious intent or typosquattinng against known packages.

igrantio-individuals