technical-writing

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow takes user prompts (e.g., from evals/cases.yaml) to generate a README/tutorial/how-to/reference and outputs a rewritten mixed-page doc, so the LLM ingests outsider-authored free text from the prompt and writes it into the resulting document that is then checked against its banlist/workflow.