tweet-writer

Warn

Audited by Snyk on Mar 17, 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's workflow explicitly requires a "Research phase (CRITICAL)" that uses WebSearch to fetch and analyze viral examples from public, user-generated sites (e.g., the "site:twitter.com OR site:x.com" query in Phase 1 and "Research phase (USE WebSearch)" instructions in How to Use This Skill), meaning untrusted third-party content is ingested and used to drive writing/decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 17, 2026, 07:05 AM
Issues
1