logic-coder
Warn
Audited by Snyk on Jul 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). 該 skill 的運行流程會從 handoff payload 讀取
enriched-spec.md(外部來源的規格文件內容)並將其「提取的文字/型別定義」用於生成 LLM 上下文與後續實作計畫;若 enriched-spec.md 由非操作用戶(如 api-enrichment/ai-pm/工程師)產出,則屬於 outsider-authored free text 進入 agent 的 LLM context。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata