react-expert

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill workflow involves processing project requirements and external command-line output from the TypeScript compiler (tsc). This represents a standard surface for indirect prompt injection, as malicious instructions could be embedded in code comments or error messages processed by the agent.
  • Ingestion points: Step 1 (Requirements analysis) and Step 4 (Compiler error review).
  • Boundary markers: None explicitly defined.
  • Capability inventory: Generates and modifies frontend source code.
  • Sanitization: Not specified for diagnostic output.
  • [COMMAND_EXECUTION]: The workflow instructs the agent to run tsc --noEmit to validate types. This is a standard development practice for TypeScript projects and does not involve unauthorized privilege escalation or persistence.
  • [EXTERNAL_DOWNLOADS]: The skill references a documentation site at jeffallan.github.io. This link belongs to the author's official GitHub Pages and is used to serve technical reference guides.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 10:42 AM
Security Audit — agent-trust-hub — react-expert