ralph-copywriter

Warn

Audited by Snyk on Mar 8, 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.md usage section explicitly says Ralph will read your existing blog posts and "analyze your Twitter/LinkedIn" and in "Research Before Writing" will "find latest data and trends" and "analyze competitor content," i.e., the agent fetches and ingests public, user-generated third‑party web/social content that it then uses to drive research, voice extraction, and writing decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 07:40 AM