neon
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of data from external database environments, which serves as a potential ingestion point for untrusted instructions embedded within schemas or query results.\n
- Ingestion points: Results from SQL execution and schema descriptions retrieved via Neon MCP tools (SKILL.md).\n
- Boundary markers: The instructions explicitly require user approval before performing any destructive database operations.\n
- Capability inventory: The agent is permitted to run SQL queries, describe schemas, and prepare migrations using the Neon MCP interface.\n
- Sanitization: The skill instructions do not specify sanitization or delimiting protocols for handling data returned from the database.\n- [NO_CODE]: This skill consists entirely of instructional markdown and configuration metadata with no accompanying scripts or executable code files.
Audit Metadata