ralph-prd-starter
Warn
Audited by Snyk on Mar 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly invokes a research subagent in Phase 8b (pm-research-specialist) and allows MCP servers such as "web-search", "brave-search", and "playwright" (PHASES.md / STATE-SCHEMA.md), producing files like ./.claude/session/research-findings.json and gdd-findings.json that the wizard reads and uses to generate questions, PRD content, and drive generation—i.e., it ingests untrusted public web and repo content that can materially influence decisions and tool actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata