The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it facilitates the retrieval and application of configuration data from external platforms (Google Cloud and Supabase) to automate authentication setup.
Ingestion points: Environment variables such as SUPABASE_ACCESS_TOKEN and GOOGLE_OAUTH_CLIENT_SECRET (documented in SKILL.md), and metadata retrieved from the Supabase Management API as noted in api-constraints.md.
Boundary markers: Absent. The instructions do not specify the use of delimiters or explicit warnings to prevent the agent from interpreting instructions that might be embedded in external configuration strings.
Capability inventory: The skill performs network operations to api.supabase.com and iap.googleapis.com, executes shell commands via pnpm, and modifies local project files as described in scaffold.md.
Sanitization: Absent. The skill documentation does not mention input validation or sanitization for credentials or configuration values before they are used in administrative API PATCH requests.

auth-launchpad