setting-up-supabase-auth-emails
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
query_logstool from the Supabase MCP server to troubleshoot hook failures by reading logs. This data is externally controlled and could potentially contain malicious instructions. - Ingestion points: Reads external Supabase project logs and processes user-provided project URLs (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or safety warnings (e.g., 'ignore instructions') to apply when the agent processes the retrieved log data.
- Capability inventory: The agent is equipped with tools to update authentication settings (
supabase-auth-emails-settings-update) and create email templates (supabase-auth-emails-starter-templates-create). - Sanitization: No explicit sanitization, validation, or filtering of the log content is described in the instructions.
Audit Metadata