trmnl-paper-screen

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly collects a device API key and MAC and instructs constructing/sending a POST that includes those credentials (and offers an option to show secrets), which requires the LLM to handle and potentially emit secret values verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill fetches and downloads runtime content from an arbitrary LaraPaper instance specified by the user (see SKILL.md "推送后审查闭环" step 2 and references/api-screens.md "推送后获取当前渲染图") and the script (scripts/push_screen.py) calls GET /api/current_screen and download_image, which the agent then uses to drive review and follow-up actions—exposing it to untrusted third‑party content that can influence behavior.