architecture-aware-init

Warn

Audited by Snyk on May 9, 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). The skill's research flow (modules/research-flow.md, "Step 2: Research Best Practices") explicitly instructs the agent to run WebSearch queries and synthesize web results, meaning it fetches and ingests untrusted public web content that feeds decisions and influences subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 9, 2026, 07:37 AM
Issues
1