x-research

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: 1.00). The skill explicitly fetches and ingests public, user-generated X/Twitter content via the Composio API (see SKILL.md and composioExec / searchTweets in index.ts), and it parses and uses tweet text and metadata as part of its search/profile/thread workflows, so untrusted third-party content can influence outputs and agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:53 PM