react-ban-use-effect

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation suggests the use of npx react-doctor@latest, which fetches and executes a package from the official npm registry, a well-known service.
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to run repository-specific lint, type, and test gates to verify the behavior of refactored code.
  • [PROMPT_INJECTION]: The skill operates on React source code, which represents a surface for indirect prompt injection. Maliciously crafted instructions within comments or data in the ingested code could attempt to influence the agent's behavior.
  • Ingestion points: The agent reads React source files (e.g., src/ProjectsTable.tsx, src/UserEditor.tsx) during refactoring and review tasks.
  • Boundary markers: None identified; there are no specific instructions to ignore embedded prompts within the processed code.
  • Capability inventory: The agent has file system write access and the ability to execute repository-specific commands (lint/test).
  • Sanitization: No input sanitization or filtering is specified for the code being processed.
  • [NO_CODE]: The skill is entirely instructional and does not include any custom executable scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 03:25 PM
Security Audit — agent-trust-hub — react-ban-use-effect