xai-sentiment

Warn

Audited by Snyk on Feb 16, 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). This skill explicitly searches and analyzes public Twitter/X posts (e.g., multiple prompts like "Search X for ..." and "Search recent posts") so it ingests untrusted, user-generated content from X that the agent is expected to read and interpret, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:28 AM