create-test-plan

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

• Third-party content exposure detected (high risk: 1.00). This skill's Step 1 explicitly requires fetching and reading PR details (title, description, changed files, comments) and Step 2 uses PR descriptions/comments/commit messages as the source of expected behavior, which means it ingests untrusted, user-generated content from public PRs/sites that can influence subsequent test-plan generation.