Back to skill

Security audit

飞书群消息撤回

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly does what it says, but it can delete Feishu messages in bulk without built-in preview or confirmation safeguards.

Review before installing. Use this only in workspaces where message recall is intended, and require the agent or operator to confirm the target chat, message IDs or time window, and message count before any batch deletion, especially when acting as a group owner or admin.

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
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)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill supports batch deletion and time-range-based recall but does not require an explicit confirmation step or present a warning before executing potentially large-scale destructive actions. In this context, a mistaken or manipulated request could cause mass removal of messages in chats, with high risk of data loss, audit disruption, and abuse by privileged users such as group admins.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes very broad phrases such as "recall" and "撤回", which can appear in normal conversation and may cause unintended activation of a destructive action. Because this skill performs message deletion/recall, accidental invocation can lead to unauthorized or irreversible content removal, especially in group contexts.

Content

No source excerpt is available for this finding.