crud-rest-controller
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it ingests data from the external project environment to drive its code generation logic.
- Ingestion points: Data enters the agent's context through multiple MCP tool calls including
get_project_summary,list_all_domain_entities,get_entity_details,list_entity_repositories,list_entity_dtos, andlist_entity_mappers. - Boundary markers: The skill lack explicit instructions to the agent to treat data returned from these tools as untrusted or to ignore embedded instructions within entity or repository names/metadata.
- Capability inventory: The skill has significant capabilities including creating new files (
Writetool in Step 5.1), modifying existing source code (Edittool in Steps 5.2, 5.3, 5.4), and altering the project's build configuration to add dependencies (Edittool in Step 6). - Sanitization: There is no explicit evidence of sanitization or escaping of the metadata retrieved from the project environment before it is interpolated into the code templates.
Audit Metadata