personal-data-harvester

Warn

Audited by Snyk on Apr 30, 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 required scraper workflows (e.g., scripts/scrape_douban.py using Playwright to navigate https://book.douban.com/people/{uid}/..., the Bilibili API interception in references/platforms.md, the Douyin short-link resolver, and Xiaohongshu Playwright scrapers) fetch and ingest public, user-generated content from third‑party websites and then load that data into a local DB which downstream agent routines (Step 6) are explicitly instructed to read and act on, so untrusted page/post content can materially influence agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 30, 2026, 04:17 PM
Issues
1