skills/magnus919/agent-skills/react/Gen Agent Trust Hub

react

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses a bounded diagnostic script, scripts/react-doctor.py, which is read-only and dependency-free.
  • [SAFE]: The script reads environment variable names to check for public prefixes but does not output their values, preventing accidental credential exposure.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project files which could contain malicious instructions. 1. Ingestion points: Local project files like package.json and .env. 2. Boundary markers: 512KB file size limit for all read operations. 3. Capability inventory: Read-only file system access within scripts/react-doctor.py. 4. Sanitization: Regex-based extraction of keys and standard JSON parsing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:57 PM
Security Audit — agent-trust-hub — react