twitter-x-gtm

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The required "Step 1: Research Hot Content" explicitly tells the agent to search Twitter (via the twitter-intel skill or WebSearch) and record/analyze viral tweets, meaning the skill ingests untrusted, user-generated public social media content that directly informs and changes the agent's content decisions and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 01:57 PM