azuresql-db-feedback

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow described in SKILL.md gathers the user’s own free-text (what happened, prompt, errors) and uses it to prefill a GitHub issue body via the gh issue create command or a prefilled issues/new URL query parameters, so outsider-authored text is directly ingested into the LLM workflow before user confirmation.