vercel-react-native-skills

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill consists exclusively of markdown documentation and code examples for mobile app development best practices.
  • [METADATA_POISONING]: The skill metadata lists the author as 'vercel', which is a trusted organization, while the provided author context is 'sovranbitcoin'. This discrepancy suggests the content may be a clone of Vercel-authored guidelines. However, since the content is purely informative and lacks any executable capabilities, this does not pose a security risk.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines rules that guide an AI agent's behavior for code generation and refactoring tasks.
  • Ingestion points: The set of rules and instructions in AGENTS.md and the rules/ directory are intended for agent ingestion.
  • Boundary markers: Not present; the guidelines are provided in standard markdown format without explicit delimiters.
  • Capability inventory: None; the skill does not contain subprocess calls, network operations, or file-writing tools.
  • Sanitization: Not applicable as the skill is static documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 03:56 AM