adversarial-audit

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

• Third-party content exposure detected (high risk: 0.90). This skill's Phase 5 "Interactive Verification" (see SKILL.md and references/verification-prompts.md) instructs the agent to open a user-provided base URL and interactively browse and evaluate the live web app, clearly fetching and interpreting arbitrary third‑party web content that can influence verification actions and severity updates.