macro-output-template

Warn

Audited by Snyk on Feb 22, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires and cites "원문 인용 (index-fetcher 결과)" and "rate-analyst"/"web-search-verifier" outputs with mandatory 출처 URLs (e.g., Bloomberg, KRX, Fed, BOK) and checklist steps that force the agent to ingest and act on open web/third-party content, so untrusted user-generated or public webpages can materially influence its analysis and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 22, 2026, 05:47 PM