supabase
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes instructions to execute a local instrumentation script at
./scripts/log-skill.shfor logging usage data. - [INDIRECT_PROMPT_INJECTION]: The skill workflows involve processing local project data, which represents a potential injection surface. 1. Ingestion points: Reads database migration files in
backend/migrations/and configuration in.env.local. 2. Boundary markers: No explicit boundary markers or delimiters are defined for the ingested file content. 3. Capability inventory: The skill can execute local scripts (log-skill.sh), create files (touch), and read files (cat,grep). 4. Sanitization: No explicit sanitization or filtering logic is provided for the data processed during the workflow. - [DATA_EXPOSURE]: The debugging documentation suggests inspecting
.env.localto verify environment variables, which is a standard procedure for troubleshooting service configurations and is consistent with the skill's purpose.
Audit Metadata