paper-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks the user to provide the KCI_API_KEY and instructs storing/using it (including example GET with &key={KCI_API_KEY}), which requires the agent to accept and embed the secret verbatim into API calls or files—an exfiltration risk.

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow (SKILL.md, "Step 2: 통합 검색") explicitly performs WebSearch on public third-party sources (RISS, DBpia, Google Scholar), requiring the agent to fetch and read untrusted public web content which can influence its summarization and follow-up actions.