byted-supabase
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an agent to process outputs from database queries and resource management commands, creating a potential surface for indirect prompt injection if those resources contain malicious instructions.
- Ingestion points: Results from tool calls including
byted-supabase-cli db query,projects list, andstorage lswhich are processed by the agent. - Capability inventory: The skill utilizes the
byted-supabase-clitool to perform file writes, database modifications, project configuration, and network-based deployments. - Boundary markers: Absent. The skill instructions do not specify explicit delimiters or 'ignore' instructions for data ingested from the database or CLI output.
- Sanitization: Absent. The skill relies on structured JSON output for tool execution but lacks specific sanitization logic for data interpolated into the agent's context.
Audit Metadata