skills/jeremylongshore/claude-code-plugins-plus-skills/designing-database-schemas/Gen Agent Trust Hub
designing-database-schemas
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.\n- Ingestion points: Business requirements and existing application source code (SKILL.md).\n- Boundary markers: Absent (SKILL.md). The instructions do not define delimiters or directives to distinguish untrusted data from agent logic.\n- Capability inventory: Access to file writing and editing tools, as well as shell-based database clients for PostgreSQL, MySQL, and MongoDB (SKILL.md).\n- Sanitization: Absent (SKILL.md). No validation or sanitization processes are defined for the input data processed by the skill.
Audit Metadata