ClawHub
Back to skill

Security audit

Feishu Progress Heartbeat

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Feishu progress-notification helper with disclosed periodic status messages and no executable code.

Install this if you want long-running Feishu tasks to post brief progress heartbeats. Review whether periodic task-status messages are acceptable in your Feishu workspace, especially for sensitive task names or confidential work, and note that the bundled examples are Chinese-oriented.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The file content is entirely in Chinese and does not offer an alternative language or indicate that Chinese is an optional or context-specific locale choice. This can violate language/locale policy when a skill effectively forces one language without user opt-in.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The percentage mapping and reply-format sections prescribe Chinese status labels and example outputs such as "进度播报" and "阻塞提醒". This is a natural-language policy issue because the skill mandates a specific language for user-facing communication without opt-in or a documented region-specific requirement.

Missing User Warnings

Low
Confidence
93% confidence
Finding
The README explicitly describes automatic periodic Feishu status messages for long-running tasks, but it does not mention user consent, visibility, or privacy considerations for outbound updates. In a messaging integration, silently sending recurring updates can leak task metadata or create unexpected external communication, even if the content is only progress information.

Static analysis

No suspicious patterns detected.