x-article-downloader

Warn

Audited by Snyk on Mar 9, 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.md explicitly opens and snapshots public X/Twitter pages (Step 1: agent-browser open "https://x.com/{user}/status/{id}" and snapshot/eval calls) and then extracts metadata, images/videos, generates tags and a condensed title and renames files (Steps 3, 5, 7, 8), so untrusted, user-generated third‑party content is read and directly influences the agent's actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 11:41 PM