abel-ask

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires web grounding: SKILL.md Step 5 (Web Grounding) and references/web-grounding.md mandate performing minimum "4 searches" of public Tier A/B/C web sources and using that external, untrusted third-party content to confirm/contradict graph findings and potentially rewrite the task or change the verdict, so the agent will fetch and act on arbitrary public web content that could contain indirect prompt injection.