cheat-init

Warn

Audited by Snyk on May 13, 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 Phase 3.5 import workflow (adapters/perf-data//README and Q2.1–Q2.3) explicitly instructs installing platform adapters (douyin-session via Playwright, youtube-data-api, bilibili-stat) to fetch user-generated posts and comments from public social platforms and then uses that scraped content to build reconstructed predictions, derive baseline_plays, and calibrate rubrics that influence later tool behavior — exposing the agent to untrusted third‑party content that can materially change its actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 13, 2026, 02:34 AM
Issues
1