The Agent Skills Directory

[SAFE]: The skill provides documentation and implementation examples for a project's authentication API using the PinMe platform.
[SAFE]: Network interactions documented target the platform's service domain (pinme.cloud).
[SAFE]: The instructions include security best practices, such as distinguishing between server-side API keys and public client configurations for Firebase.
[PROMPT_INJECTION]: The skill documents methods for retrieving user-controlled data (e.g., display names and emails) from the authentication service, which creates an attack surface for indirect prompt injection.
Ingestion points: User profile fields such as display_name and email returned by the list_users, getAuthUser, and verify_token API endpoints in SKILL.md.
Boundary markers: None identified; the provided code snippets show direct processing of JSON responses without the use of delimiters or isolation instructions.
Capability inventory: The documented integration utilizes network capabilities via fetch and potentially interacts with a database (D1Database) as shown in the environment configuration in SKILL.md.
Sanitization: No sanitization or validation logic is present in the code examples to filter malicious content within user-supplied profile data.

pinme-auth