Security audit

Feishu/Lark

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a legitimate Feishu/Lark integration, but it can read and modify workspace chats, documents, drive files, wiki pages, and bitable data when configured.

Install only if you intend to connect an agent to Feishu/Lark. Grant the Feishu app the minimum scopes needed, keep permission management disabled unless required, and consider disabling doc, drive, wiki, bitable, dynamic agent creation, or auto-join features you do not need. Be aware that some skill triggers are generic, so users should be explicit when they do or do not want Feishu used for cloud docs, drive folders, or wiki requests.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The description says to activate when the user mentions "Feishu docs, cloud docs, or docx links." While "Feishu docs" is specific, "cloud docs" and generic "docx links" are broad enough to overlap with ordinary requests unrelated to this skill. The file does not provide narrower scope limits or negative examples to prevent unintended invocation.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The activation description uses broad phrases like 'cloud space,' 'folders,' 'Drive files,' and 'document comments,' which can match many ordinary user requests outside the intended Feishu-specific context. This can cause the skill to activate unnecessarily and access or expose Feishu Drive data in situations where the user did not clearly intend to use this integration.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The activation description is broad enough to trigger on common terms like 'knowledge base', 'wiki', or 'wiki link' in ordinary conversation, which can cause the skill to activate outside the user's intended scope. While this does not directly expose data or execute unsafe actions, it can lead to unintended tool use, context confusion, and increased risk if downstream actions are sensitive.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/client-DMbIL3UH.js:19
Evidence: const envRaw = process.env[FEISHU_HTTP_TIMEOUT_ENV_VAR];