The Agent Skills Directory

[PRIVILEGE_ESCALATION]: The installation instructions for Linux systems utilize sudo to move the Supabase CLI binary to a protected system directory (/usr/local/bin/). While this is a common practice for global tool installation, it requires elevated permissions.
[EXTERNAL_DOWNLOADS]: The skill fetches the official Supabase CLI directly from its GitHub release page. This is a well-known service, and the download targets the official repository of the project supported by the skill.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where untrusted data could influence agent actions or system commands.
Ingestion points: supabase/functions/my-function/index.ts (processing request JSON data) and SKILL.md (interpolating shell variables like RECIPIENTS and email into command payloads).
Boundary markers: The provided examples lack delimiters or instructions to ignore potentially malicious embedded content within the processed data.
Capability inventory: The skill possesses extensive capabilities including code deployment (supabase functions deploy), secret management (supabase secrets set), and arbitrary network requests via curl and Deno's fetch API.
Sanitization: No explicit sanitization, validation, or escaping of external inputs is demonstrated in the shell scripts or TypeScript templates before the data is used in logical operations or payload construction.
[COMMAND_EXECUTION]: The skill makes extensive use of the supabase CLI to perform administrative tasks, project management, and environment configuration through shell commands.

supabase-edge-functions