ClawHub
Back to skill

Security audit

飞书多Agent群聊通信

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for setting up Feishu-based multi-agent chat routing, with expected third-party messaging exposure but no hidden code or automatic execution.

Install only if you intend to route agent prompts and responses through Feishu. Keep bots limited to the needed groups, review Feishu app permissions, and avoid sending secrets, credentials, personal data, or regulated information unless your organization has approved that data flow.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill describes routing messages among multiple AI agents through Feishu groups, bots, WebSocket/Gateway components, but it does not explicitly warn users that prompts, outputs, and possibly sensitive task data will be transmitted to Feishu and shared across multiple services/bots. This omission can cause users to unknowingly expose confidential information to third-party infrastructure and additional agents, increasing privacy and data-handling risk in a multi-hop communication setup.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This manifest file includes very broad activation-like keywords such as "feishu", "websocket", and "multi-agent" alongside more specific phrases. In a manifest context, such generic terms can make the skill match loosely related user requests, and the file provides no constraints or negative examples to narrow when invocation should or should not happen.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

Several user-facing manifest fields, including pricing and dependency descriptions, are written only in Chinese even though the file also defines English keywords. This creates a locale-specific experience without any visible opt-in or alternate language path, which may conflict with language-choice expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains user-facing operational guidance only in Chinese, and it does not provide an opt-in, alternative language, or justification for a Chinese-only locale. Under the policy rule for natural-language violations, forcing a single language without user choice can be considered a locale-policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file contains user-facing operational guidance only in Chinese, beginning with the title and continuing through all troubleshooting steps. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.