ClawHub

飞书群消息撤回

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent but needs review because it can recall many Feishu messages through the user's account without documented confirmation safeguards.

Install only if you intend to let an agent recall Feishu messages using your account. Before any bulk or time-range recall, require the agent to show the chat, time window, message count, senders, and message IDs, then obtain explicit confirmation; use a least-privileged Feishu account where possible.

SkillSpector

By NVIDIA
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
92% confidence
Finding
The trigger list includes very broad terms such as "recall" and "撤回", which are common in ordinary conversation and can cause unintended activation of a destructive action. In this skill's context, accidental invocation is more dangerous because the documented behavior includes deleting single messages, bulk messages, and time-range message recalls under the user's identity.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill describes batch and time-range recall flows without requiring any user-facing warning or confirmation about the scope and irreversibility of the operation. Because this action deletes chat history as the user and may affect many messages at once, missing safeguards materially increases the risk of accidental or socially engineered mass deletion.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal