schema-design
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to provide architectural guidance and generate SQL templates. It does not perform network operations, access sensitive credentials, or execute the code it generates.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted external data (existing schema files, migration history, and feature requirements) to generate SQL output.
- Ingestion points: Reads existing schema files, migration history, and ORM models during Step 1, and processes feature requirements provided in the agent's context.
- Boundary markers: The instructions do not define specific delimiters to isolate analyzed data from the agent's core instructions.
- Capability inventory: The skill is limited to text generation; it has no capabilities for file-system modification, network exfiltration, or command execution (as noted in the Scope Constraints).
- Sanitization: The skill includes an 'Input Sanitization' section claiming inputs are treated as read-only analysis targets, which serves as a conceptual constraint for the agent.
Audit Metadata