The Agent Skills Directory

[METADATA_POISONING]: The skill's YAML frontmatter identifies the author as 'supabase', which conflicts with the platform-provided author 'tanuj0071'. This discrepancy is misleading regarding the skill's provenance and official status.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process external content from documentation pages and search tools. This creates an ingestion surface for potentially untrusted content that could influence agent behavior.
Ingestion points: The search_docs tool and documentation fetched from supabase.com.
Boundary markers: The skill lacks explicit instructions or delimiters to isolate fetched documentation from the agent's core instructions.
Capability inventory: The agent possesses capabilities for database execution (execute_sql), CLI migration management (supabase db pull), and network status checks (curl).
Sanitization: No sanitization or filtering of fetched documentation is defined in the instructions.
[EXTERNAL_DOWNLOADS]: The skill references and fetches documentation and configuration from official Supabase domains and GitHub repositories.
[COMMAND_EXECUTION]: The skill utilizes the supabase CLI and standard shell commands for development tasks and server health checks.

supabase