unfollow-management

Warn

Audited by Snyk on Feb 28, 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 requires navigating to public X/Twitter pages (e.g., "x.com/USERNAME/following" in SKILL.md) and its scripts (references/script-details.md) read DOM elements like user cells and usernames from those public, user-generated pages and then make unfollow decisions and clicks based on that content, which exposes the agent to untrusted third-party content that can influence actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 09:53 AM