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
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 06:25 PM
Issues
1