architecture-agent-creation

Warn

Audited by Snyk on Feb 18, 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). This skill's SOP and Tools sections explicitly require using WebFetch/WebSearch to gather "official documentation" and "community resources" (SOP-1 Research Phase and Tools Used), so the agent fetches and ingests open/public and user-generated web content that it will read and incorporate into agent prompts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 18, 2026, 12:01 AM