supabase

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands like curl, grep, cut, and sed to interact with the Supabase Management and PostgREST APIs. These commands are used to manage environment variables and perform database operations on official Supabase domains (supabase.co and supabase.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external database sources through API responses and processes it using Python. While this constitutes an attack surface if the database content is maliciously crafted by an external party, the risk is mitigated by the skill's focus on structured data analysis (e.g., counting records, calculating revenue) rather than interpreting the data as instructions.
  • Ingestion points: API responses from curl commands in SKILL.md.
  • Boundary markers: None explicitly defined for API data.
  • Capability inventory: Subprocess execution via Bash tool, file system access via Read/Write tools.
  • Sanitization: Standard JSON parsing using the json Python module.
  • [DYNAMIC_EXECUTION]: Uses inline Python scripts (python3 -c) to parse JSON output from API calls. These scripts are generated from static templates to perform specific calculations like MRR (Monthly Recurring Revenue) and conversion funnels, which is a standard method for data processing in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 08:19 PM