react-refactor
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to ingest and refactor untrusted user source code, which presents a surface for indirect prompt injection if the user code contains malicious instructions.\n
- Ingestion points: External React source code files provided by the user.\n
- Boundary markers: None provided to isolate untrusted user data from agent instructions.\n
- Capability inventory: Code generation and filesystem modification via the agent's core capabilities.\n
- Sanitization: None provided.\n- [NO_CODE]: The skill consists exclusively of Markdown files and documentation; it contains no executable scripts, binaries, or automated tooling.
Audit Metadata