deploying-supabase-application

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository files (such as config.toml, SQL migrations, and Edge Functions) to identify the Supabase root and configuration. Maliciously crafted files could attempt to inject instructions to the agent to influence its behavior during the discovery or validation phases.
  • Ingestion points: config.toml, migrations/, and functions/ directories as defined in discovering-supabase-root.md.
  • Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore embedded instructions when reading these files.
  • Capability inventory: Execution of supabase and deno CLI commands based on discovered project structure.
  • Sanitization: No explicit sanitization or validation of file content is requested before processing.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (supabase db start, supabase db reset, supabase db lint, deno check, deno test) in the context of the repository. While these are standard Supabase and Deno development tools, they are executed based on findings within the repository, which presents a potential command injection surface if the repository content is malicious.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 05:49 AM
Security Audit — agent-trust-hub — deploying-supabase-application