Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward Feishu Bitable query helper that uses local Feishu credentials to read table records, with no evidence of hidden persistence, destructive actions, or unrelated data exfiltration.
Install only if you intend agents to query Feishu Bitable data using the Feishu app credentials stored in ~/.openclaw/openclaw.json. Treat results as organizational data, and prefer explicit app tokens, table IDs, filters, and field selections so the agent retrieves only the records needed.
The skill invokes a Python script that performs network-backed Feishu queries, but the manifest declares no explicit tool scope or permission boundaries. Without allowed-tools or permissions metadata, an agent may activate this skill without clear policy enforcement, increasing the chance of unintended external data access.
The activation text is broad enough to match many ordinary data-query requests, which can cause the skill to trigger in contexts where the user did not explicitly intend Feishu Bitable access. Because the skill can query remote records and use stored credentials, overbroad activation increases the risk of unnecessary or privacy-impacting data retrieval.
The skill states that credentials are automatically read from ~/.openclaw/openclaw.json, but it provides no user-facing warning or consent boundary around secret use. This is dangerous because the skill can silently leverage locally stored Feishu app credentials to access organizational data, especially when combined with broad activation criteria.
This code loads appId and appSecret from a local config file and immediately sends them in an HTTP request to obtain a tenant access token. Although network access is inherent to the tool's purpose, there is no explicit disclosure in the docstring, comments, or runtime output that local credentials will be read and transmitted for authentication.
This markdown file is entirely written in Chinese, starting with the title at L01, and does not state that the reference is intended only for Chinese-speaking users or a China-specific deployment context. Under the language/locale policy, forcing a specific language without opt-in or justification can be a policy violation.
