mybatis-plus-generator
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it ingests and processes untrusted data (database schemas and SQL CREATE TABLE statements) to generate source code and documentation.
- Ingestion points: User-supplied database connection metadata and SQL table definitions (Step 1 and Step 6 in
SKILL.md). - Boundary markers: The instructions do not specify the use of strict delimiters or escaping mechanisms when the agent interpolates table/field comments directly into generated JavaDoc or API annotations (e.g., Swagger
@ApiModelPropertyor OpenAPI@Schema). - Capability inventory: The skill facilitates the creation and modification of multiple source files across various layers (Entity, Mapper, Service, Controller, DTO, etc.) on the local file system.
- Sanitization: There are no explicit instructions for the agent to sanitize or filter potential instructional content embedded within the schema comments, which could lead to the agent following malicious instructions hidden in the data.
Audit Metadata