architecture-aware-init

Warn

Audited by Snyk on Feb 27, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). Yes — Step 2 "Research Best Practices (arch-init:research-completed)" explicitly instructs performing WebSearch queries (e.g., WebSearch("...") in the SKILL.md and example session) to fetch and synthesize online/public web content, which the agent will read and use to drive architecture decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 06:50 PM