automation-coverage

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs (Step 1) to clone e2e tests from a user-provided git URL into .testclaw-context/e2e-tests and then reads/parses those test files (Step 3) via grep to build the coverage mapping, meaning arbitrary public/untrusted repository content is ingested and can directly influence mapping and subsequent test-run decisions.