skills/breakthrough-edu/breakthrough-database-skills/breakthrough-base-schema-design/Gen Agent Trust Hub
breakthrough-base-schema-design
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data during a multi-phase guided interview with the user. This data is subsequently used to populate a 'Base Blueprint' document. While the skill primarily produces documentation, the interpolation of user-supplied strings into the final output without explicit boundary markers or sanitization logic constitutes an indirect prompt injection surface.
- [SAFE]: The instructions and referenced files focus on business logic, database normalization rules, and Lark-specific formulas. No evidence was found of network exfiltration, hardcoded credentials, or unauthorized access to sensitive file paths. The skill explicitly states it is for design rather than physical building or API interaction.
Audit Metadata