personalization-hooks

Warn

Audited by Snyk on Feb 17, 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 expects and shows examples of ingesting public social-media content (e.g., "Turn this LinkedIn post into a strong hook opening line: [paste post]") and references finding content to hook on, which means the agent would read/interpret untrusted, user-generated third-party posts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 12:22 AM