cold-email
Warn
Audited by Snyk on Feb 20, 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's personalization workflow explicitly instructs building AI prompts for external enrichment (e.g., the personalization SKILL.md example: "Find the most recent LinkedIn post by {{firstName}}... Summarize the post's main argument") and other guidance mentions scraping public site case studies (resources/frameworks/cold-email-mastery.md), meaning the agent is expected to fetch and interpret user-generated public content (LinkedIn/posts, website case studies) that could materially change messaging and actions.
Audit Metadata