hotfix
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). 该 skill 运行时会“加载并遵循 lfg skill 的完整流程”,而 lfg 的各步骤/脚本化门禁与 CI watch/compound 可能会读取 GitHub issues/PRs/讨论等由外部作者撰写的文本并喂入 LLM;SKILL.md 未排除这些 outsider 内容。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata