setting-up-supabase-auth-emails
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and analyze Supabase logs to debug failed authentication hooks. Since log entries can be influenced by external actors (e.g., through failed login attempts with malicious payloads), this creates a surface for indirect prompt injection.
- Ingestion points: The
query_logstool is used to read Supabase's authentication and system logs. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within log data.
- Capability inventory: The agent has the ability to update project settings and secrets via the
supabase-auth-emails-settings-updatetool and modify email templates. - Sanitization: There are no explicit instructions for the agent to sanitize or validate the log content before processing it for debugging.
Audit Metadata