Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Feishu multi-bot discussion helper, but its automatic broad triggers and group-posting behavior need careful review before use.
Review this before installing in any real Feishu group. Only enable it in chats where participants expect automated multi-bot replies, use explicit command-style triggers if possible, restrict who can invoke it, and clarify exactly where bot credentials are stored.
The skill documentation and invocation examples are entirely specified in Chinese, including the required trigger phrases, with no indication that users may choose another language or locale. This creates a natural-language policy concern because the skill appears to require a specific language without opt-in or documented justification.
The trigger phrases are broad, natural-language expressions likely to occur in normal group conversation, which can cause the skill to activate unintentionally. In this skill's context, accidental activation is more dangerous because it can spawn multiple bot personas and send messages into a shared Feishu group, causing spam, confusion, or unauthorized automated responses.
The description on L04 is written as a Chinese-only user-facing capability statement and indicates the skill is intended for a Chinese-language Feishu group context, but there is no indication of language choice, opt-in, or documented locale limitation. This can violate language/locale policy when a skill implicitly restricts interaction to one language without making that constraint explicit and justified.
The skill documentation earlier states that bot credentials are configured in config.json and even provides a config.json example, but L75 says credentials are read from openclaw.json under channels.feishu.accounts. These are mutually inconsistent configuration sources, so the documentation actively contradicts itself about where secrets are actually loaded from.
No suspicious patterns detected.
