agent-feature-analyst

Warn

Audited by Snyk on Mar 5, 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 Analysis Workflow explicitly requires "Research context (WebSearch for competitive analysis)" and the Imported Agent Spec lists tools like WebSearch, WebFetch and mcp__brave__brave_web_search, meaning the agent will fetch and read open/public third‑party web content that can influence decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 01:13 AM