spec-writer
Warn
Audited by Snyk on Mar 15, 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 instructs in "1. 니즈 정렬 및 현황 파악" that the agent should collect "도메인 지식, 유사 시스템 패턴, 유사 솔루션 사례 등 인터넷을 통해 습득 가능한 지식" via sub-agents, which means it ingests public web content (untrusted third-party sources) and uses that information to influence spec decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata