schema-architect
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted data such as business requirements and existing database schema files (
schema.prisma,.sql). This creates a surface for indirect prompt injection if those files contain malicious instructions. - Ingestion points: Business requirements and schema files mentioned in the Execution Context of
SKILL.md. - Boundary markers: The skill does not define specific delimiters to isolate external data from its core instructions.
- Capability inventory: The skill writes generated reports and JSON outputs to the local filesystem (
docs/database-report/). - Sanitization: No input sanitization or validation of the requirements text is specified.
- [NO_CODE]: The skill consists entirely of natural language instructions and YAML configuration. It does not include or execute any scripts, binaries, or shell commands.
Audit Metadata