promo-creator-skills
Warn
Audited by Snyk on May 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and ingest public third‑party content — e.g., promo-brief SKILL.md says to "抓取 README、首页文案、产品文档" from GitHub/website URLs and promo-asset-producer SKILL.md requires "浏览器搜索下载" Pack B assets — and those untrusted web-sourced materials are required inputs used to generate the brief, storyboard, asset plan, EDL, music prompts and rendering decisions, so they could enable indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill's master-edit.html template includes external runtime dependencies fetched during rendering—notably the GSAP script (https://cdn.jsdelivr.net/npm/gsap@3/dist/gsap.min.js) and Google Fonts (https://fonts.googleapis.com/css2?family=Inter:...), which will be downloaded and execute/affect the render environment and are required by the generated HyperFrames HTML.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata