fe-test
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes external source files to generate test code, creating an attack surface for instructions embedded within those files. • Ingestion points: Source files analyzed via $ARGUMENTS. • Boundary markers: Absent; the skill does not use delimiters to wrap ingested code content. • Capability inventory: File system write access (creating .test.ts files). • Sanitization: None; ingested code is processed directly by the LLM.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill references standard, well-known frontend libraries (Vitest, React Testing Library, MSW, Zustand) and does not perform any automated package installation or remote script execution.
Audit Metadata