pp-tiktok-shop

Warn

Audited by Snyk on May 8, 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's Agent Mode and agent-context command (see "Agent Mode" and the Command Reference entries like orders list, orders get, shops info, and agent-context in SKILL.md) cause the agent to fetch and consume JSON data from TikTok Shop Partner Center APIs (third-party shop/product/order data including user-generated buyer/product fields), which the agent is expected to read and use to decide next actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires installing and running remote installer code at runtime via "npx -y @mvanhorn/printing-press install tiktok-shop --cli-only" and/or "go install github.com/mvanhorn/printing-press-library/library/commerce/tiktok-shop/cmd/tiktok-shop-pp-cli@latest", which fetches and executes external code that the skill depends on.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 8, 2026, 06:07 PM
Issues
2