react-components

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external design data, which could contain malicious instructions designed to influence the agent's code generation.
  • Ingestion points: Design JSON and HTML content are fetched from the stitch MCP tool and external URLs (SKILL.md steps 2 and 4).
  • Boundary markers: The skill lacks explicit instructions for the agent to ignore or delimit instructions that might be present in the external HTML content.
  • Capability inventory: The skill can execute bash commands, install dependencies, write to the filesystem, and run validation scripts.
  • Sanitization: No sanitization is performed on the incoming HTML design data before it is interpreted by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill uses curl within a local bash script (scripts/fetch-stitch.sh) to download design assets from URLs retrieved from the Stitch design tool.
  • [COMMAND_EXECUTION]: The skill executes various commands to fulfill its purpose, including npm install for dependency management, a bash script for asset fetching, and a Node.js script for AST-based code validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:55 AM
Security Audit — agent-trust-hub — react-components