nexus-sdk-integration

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [Unverifiable Dependencies] (MEDIUM): The skill instructs the user to install '@avail-project/nexus-core'. The '@avail-project' organization is not listed as a trusted source, presenting a risk of supply chain vulnerabilities or dependency confusion.
  • [Indirect Prompt Injection] (LOW): The skill defines an attack surface by accepting untrusted user inputs (wallet details, network configuration) to generate integration logic. 1. Ingestion points: Target runtime, network selection, and wallet connection details. 2. Boundary markers: Absent. 3. Capability inventory: Orchestrates subskills and recommends command execution for package installation. 4. Sanitization: Not specified in the provided instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:27 PM