keyapi-tiktok-ecommerce

Warn

Audited by Snyk on Mar 24, 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 calls KeyAPI MCP tools at https://mcp.keyapi.ai (see SKILL.md and scripts/run.js) to fetch TikTok Shop data—including product/share-link resolution, customer reviews, videos, and livestream content—which are public, user-generated third‑party sources that the agent ingests and uses to drive analysis and follow‑up actions, allowing arbitrary third‑party content to potentially influence behavior.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill connects at runtime to the KeyAPI MCP server (default server URL https://mcp.keyapi.ai, e.g. https://mcp.keyapi.ai/tiktok/mcp) and uses client.listTools / client.callTool to fetch tool schemas and invoke remote tools, meaning remote content/logic executes and controls the skill's behavior and responses.

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
Mar 24, 2026, 12:10 PM
Issues
2