skills/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/supabase/Gen Agent Trust Hub
supabase
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (databases, storage, and function logs) and possesses capabilities that could be influenced by malicious content within those sources.\n
- Ingestion points:
supabase db pull,supabase storage cp, andsupabase functions logsinSKILL.md.\n - Boundary markers: Absent.\n
- Capability inventory:
supabase db execute,supabase functions deploy, andsupabase secrets setinSKILL.md.\n - Sanitization: Absent; the skill relies on the Supabase CLI's native handling and the agent's internal safety guardrails.\n- [COMMAND_EXECUTION]: The skill utilizes the standard
supabaseCLI for local and remote project management, which is the expected and legitimate behavior for this integration.
Audit Metadata