daily-briefing

Warn

Audited by Snyk on Mar 18, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill fetches and parses open/public, user-generated sources — e.g., the Karpathy OPML Gist (https://gist.githubusercontent.com/.../hn-popular-blogs-2025.opml) and the RSS feeds it lists, scrapes GitHub Trending (https://github.com/trending), reads Hacker News via the Firebase API, Readhub API, and V2EX hot topics — and directly uses that untrusted content to build and send the agent's daily briefings, so third-party content can influence what the agent publishes.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 03:23 AM
Issues
1