twitter

Warn

Audited by Snyk on Mar 1, 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). This skill's SKILL.md includes curl calls to the Twitter API v2 endpoints (tweets/search/recent, users/by/username, users/:id/tweets) that fetch user-generated, untrusted tweets and profiles, which the agent would read and could be influenced by instructions in that content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:18 AM