react-expert
Fail
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user requirements to generate React code and subsequently executes validation tools (TypeScript compiler) and test suites. This creates an attack surface where malicious input could attempt to influence the generated code or subvert the validation environment.\n
- Ingestion points: The skill ingest user requirements for component hierarchy, state, and data flow in step 1 of the Core Workflow (SKILL.md).\n
- Boundary markers: Includes explicit "MUST DO" and "MUST NOT DO" constraints to guide agent behavior and limit output scope.\n
- Capability inventory: Invokes shell commands for type checking (tsc --noEmit) and test execution (vitest/jest) as part of the implementation and validation workflow.\n
- Sanitization: No explicit data sanitization or input validation logic is provided in the instructions beyond standard tool-based verification.\n- [EXTERNAL_DOWNLOADS]: The skill references an external documentation URL (jeffallan.github.io) which is an author-owned resource. Although this is a vendor resource, automated reputation scanners have flagged the domain as a potential risk.\n- [COMMAND_EXECUTION]: The workflow requires the agent to execute command-line tools such as the TypeScript compiler and test runners to ensure code quality and correctness.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata