supabase-audit-buckets-read
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to download and sample content from external Supabase storage buckets. This represents a vulnerability surface where malicious instructions contained within sampled files could influence the agent's behavior.
- Ingestion points: External storage bucket objects accessed via curl commands as described in SKILL.md.
- Boundary markers: The instructions lack specific delimiters or guardrails to ensure the agent ignores any natural language instructions discovered inside the sampled file content.
- Capability inventory: The skill allows for local file writes to .sb-pentest-context.json and .sb-pentest-audit.log, and network operations using curl to interact with the Supabase API.
- Sanitization: No sanitization, filtering, or escaping logic is defined for the content retrieved from external files before it is analyzed by the agent.\n- [COMMAND_EXECUTION]: The skill utilizes the curl command-line tool to perform network requests against the Supabase Storage API for listing files, fetching metadata, and downloading samples.
Audit Metadata