ClawHub
Back to skill

Security audit

Feishu At Mention

Security checks for vulnerabilities and agentic risk

Overview

This skill provides Feishu @mention formatting guidance with a scoped ID lookup example, and I found no hidden code, persistence, or deceptive behavior.

Before installing, understand that this skill may guide your agent to use Feishu member lookup when an open_id is missing, which can expose chat member identity data to the active Feishu integration. Use it only in workspaces where the agent is allowed to prepare messages and mention users or everyone in a chat.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The example hardcodes the locale key `zh_cn`, and the document is entirely written as Chinese-only guidance without stating that the skill is region- or language-specific. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation.

Description-Behavior Mismatch

Low
Confidence
84% confidence
Finding
The manifest description scopes the skill to choosing the correct @mention tag format for text, post, and interactive messages. However, the document also extends into identity/member lookup guidance by recommending a `feishu_chat action=members` API call, which is beyond pure message-formatting behavior.

Static analysis

No suspicious patterns detected.