The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @neondatabase/auth package from the NPM registry. This package is maintained by the skill authoring organization.
[INDIRECT_PROMPT_INJECTION]: The skill guides the creation of components and server actions that process untrusted data, which could serve as a vector for indirect prompt injection if the agent interacts with these inputs.
Ingestion points: User data is ingested via formData in the signIn and signUp actions (SKILL.md) and through URL parameters in the AuthPage component.
Boundary markers: There are no explicit boundary markers or warnings to the agent regarding potential instructions embedded in user-supplied data within the code templates.
Capability inventory: The skill context includes access to tools such as Bash, Write, Read, Edit, Glob, and Grep, which could be exploited if malicious data is processed without isolation.
Sanitization: The provided setup examples do not include explicit sanitization or validation logic for the input fields (email, name, password) beyond standard type casting.

neon-auth-nextjs