ClawHub
Back to skill

Security audit

Feishu Card Builder Free

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Feishu card-message helper, but users should treat sending messages and uploading local files as live external actions.

Install only if you intend to let an agent use your Feishu app credentials to send messages and upload selected local images or file contents. Verify the target user or group ID and preview sensitive content before sending, because recipients will receive whatever file, image, or text you provide.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation describes sending messages, uploading local images, and using application credentials, but does not warn users about visible side effects, possible disclosure of local file contents, or the sensitivity of Feishu app credentials. In an agent setting with exec access, missing user-visible risk disclosure makes accidental exfiltration or unintended external actions more likely.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill declares broad trigger keywords unrelated to Feishu card building, including generic copywriting and content creation scenarios. This can cause the agent to invoke a message-sending skill in contexts where the user did not intend outbound communication, increasing the chance of accidental data disclosure, unintended message delivery, or misuse of configured Feishu credentials.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

技能名称和整份说明均以中文呈现，且未说明是否支持其他语言或允许用户按偏好选择语言。对面向“任意AI Agent”的通用技能而言，若默认固定语言而无用户选择，可能构成语言/地区策略上的不透明约束。

Content

No source excerpt is available for this finding.