ClawHub
Back to skill

Security audit

AI工作日记

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Feishu work-journal publisher, with some broad activation wording users should watch but no hidden or destructive behavior found.

Before installing, confirm you want an agent to create Feishu Wiki documents using your local Feishu session. Use explicit commands that mention Feishu, review the generated journal and screenshots for sensitive work details, and avoid saving or sharing real Wiki URLs, node tokens, passwords, App Secrets, or refresh tokens.

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
89% confidence
Finding
The trigger list includes broad, everyday phrases such as '写今天的记录' and '每天用 AI', which can match ordinary conversation and cause the skill to activate when the user did not intend to publish or store content in Feishu. In this skill's context, unintended activation matters because it can lead to drafting or attempting to upload potentially sensitive work summaries to an external knowledge base.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The read_when conditions are broad and overlap with common productivity topics like '排障 / 提效 / 探索记录落库', making the skill eligible in situations that may not actually call for Feishu publication. In context, this increases the chance of unintended collection, transformation, or external posting of user work details, which may include internal operational information.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.