Security audit

Feishu Cron Delivery

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Feishu scheduling helper; it can create real recurring Feishu messages, but that behavior matches its stated purpose.

Install only if you intend to manage OpenClaw cron jobs that send Feishu messages. Use test recipients first, replace OPEN_ID/account/message text with your own values, confirm the language and recipient before scheduling recurring jobs, and review the generated smoke-test command before running it.

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 (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description is broad enough to match ordinary scheduling, reminder, or outbound-message requests, which can cause the agent to invoke this skill outside its narrowly intended Feishu-delivery repair use case. That creates a scope-control problem: users may be routed into a skill that changes delivery semantics, routing, and session mode in ways they did not ask for, increasing the chance of unintended message delivery or misconfiguration.

Natural-Language Policy Violations

Medium

Confidence: 81% confidence
Finding: The examples hard-code Chinese-language output directed at a named recipient without documenting that Chinese is required by the user, tenant policy, or channel configuration. In practice this can cause unintended language selection, recipient-context leakage in copied examples, and behavior that overrides user preference or locale expectations when the pattern is reused.

Static analysis

No suspicious patterns detected.