Camp Planner Setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to collect an API key from the user and write it verbatim into the thin config file (.claude/kids-camp-planner.local.md), which requires the LLM to handle and produce secret values directly.

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

• Third-party content exposure detected (high risk: 0.90). The skill's setup workflow (see "3-Tier School Calendar Lookup" in Step 2 and the notes in Step 1) explicitly instructs the agent to conduct web searches and download school calendar PDFs from public websites or user-provided URLs, then extract and save calendar data that will be read/interpreted and used to drive planning decisions—exposing the agent to untrusted third-party content that could carry indirect prompt injection.