temporal-awareness

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow (SKILL.md plus references/bootstrap.md, references/recency-triage.md and references/verification-patterns.md) explicitly instructs the agent to "verify against current authoritative sources" and to "browse or search authoritative sources" when recency_guard classifies a prompt as live-verify, which requires ingesting content from public third‑party websites that can materially influence subsequent actions.