skills/giuseppe-trisciuoglio/developer-kit-claude-code/unit-test-application-events/Gen Agent Trust Hub
unit-test-application-events
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) inherent to its design as a code-generation utility.
- Ingestion points: The skill ingests user-provided Java source code, service definitions, and event requirements from the agent context (e.g., via the
Readtool) to produce unit test files. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instruction' warnings to prevent the agent from inadvertently following instructions found within processed source code.
- Capability inventory: The skill is granted access to the
WriteandBashtools, which enable the creation and execution of files based on generated content. - Sanitization: No explicit input validation or sanitization logic is provided to filter the user-supplied source code before it is interpolated into test templates.
Audit Metadata