feishu-cli-chat

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes explicit examples and guidance to pass user access tokens directly on the command line (e.g., --user-access-token ) and to set FEISHU_USER_ACCESS_TOKEN, which encourages embedding secret values verbatim in commands and thus risks exfiltration.

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests user-generated chat content from Feishu via APIs (e.g., "feishu-cli msg history", "search messages", and the "完整示例：获取并总结群聊最近 N 条消息" flow in SKILL.md, including external/cross-tenant "外部群"), and then reads/summarizes/acts on those messages, so untrusted third-party content could carry instructions that influence agent behavior.