news-digest-video-agent

Warn

Audited by Snyk on Apr 14, 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's mandatory workflow (SKILL.md and AGENTS.md) requires using the browser-use skill to visit and ingest content from open/public third-party sources—explicitly YouTube videos, X.com (tweets), and news websites like BBC/AP/Reuters—which the agent must read and act on (select clips, write voiceovers, and drive build decisions), exposing it to untrusted user-generated or public web content that could carry indirect prompt-injection instructions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 14, 2026, 03:14 PM
Issues
1