qa-tester-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly scans page HTML for secret patterns and instructs logging/pasting matched secrets and console logs into reports, which requires emitting sensitive values verbatim (high exfiltration risk).

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to load and inspect arbitrary web pages (e.g., page.goto(url), const html = await page.content(), page.evaluate(...), response.headers()) and to act (stop tests, report severity, run payloads) based on that untrusted page content, so it clearly ingests and trusts third-party content from public URLs.