learning-graph-generator

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly reads and processes user- or repo-provided files (e.g., docs/course-description.md, learning-graph.csv, taxonomy-names.json/metadata.json) and even suggests cloning a public GitHub repo (https://github.com/dmccreary/intelligent-book-template), so it ingests untrusted third‑party/user-generated content that the agent is expected to read and interpret.