primitives-showcase

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local script (scripts/run) to execute its core logic via Node.js. This script handles session management and workflow advancement by executing a local JavaScript binary.
  • [PROMPT_INJECTION]: Instructions use structured XML tags (e.g., <system>, <prompt>, <rendered>) to define system personas, task instructions, and output formatting. These tags guide the agent's interaction and response style within the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 08:55 PM
Security Audit — agent-trust-hub — primitives-showcase