build-data-pipeline

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a telemetry system that tracks usage metrics (skill name, phase, status, platform). This system is transparently documented in the bash preamble, respects a 'telemetry-prompted' flag, and allows users to opt-in or out. Data is sent to a user-configured endpoint via a POST request.
  • [SAFE]: Local state and configuration are managed within the ~/.superstack/ directory. This is standard behavior for CLI-based developer tools to maintain context across sessions.
  • [SAFE]: The skill references well-known and trusted services like Helius for Solana infrastructure and Convex for backend services. Command examples (e.g., curl for API interactions, npx for MCP setup) are routine developer tasks and do not involve suspicious execution patterns.
  • [SAFE]: The skill reads and updates a local .superstack/build-context.md file to maintain development state. While this is an ingestion point for external data, the file is managed by the skill itself, and the risk of indirect prompt injection is negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 11:04 AM
Security Audit — agent-trust-hub — build-data-pipeline