react-context-setup
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user requests and frontend code to provide setup guidance, which can be leveraged for indirect prompt injection.\n- Ingestion points: The skill reads external data such as React source files and user-provided configuration requirements via the Read tool.\n- Boundary markers: The instructions do not define clear delimiters or warning patterns to prevent the agent from following instructions embedded within the processed code.\n- Capability inventory: The skill is granted extensive capabilities via its allowed tools, including unrestricted bash command execution and file modification (Write, Edit).\n- Sanitization: There is no evidence of input validation or content filtering to identify or neutralize malicious payloads in processed data.
Audit Metadata