ClawHub

Feishu Book Match

Security checks across malware telemetry and agentic risk

Overview

The skill does what it says, but it can bulk-edit a Feishu database and suggests unattended runs without enough safeguards.

Install only if you intend to let the agent write to the target Feishu Bitable. Confirm the table, fields, Feishu account, and Chrome profile first; run a small preview before writing; review batches as they complete; and avoid unattended cron/background execution unless you set explicit limits, logs, stop conditions, and a recovery plan.

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
91% confidence
Finding
The skill description includes broad trigger phrases such as "match books" and "or similar tasks," which can cause the agent to invoke this skill in contexts the user did not specifically intend. Because the skill performs external lookups and writes back to a Feishu Bitable, accidental invocation can lead to unintended data modification at scale.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill is designed to batch-update Feishu Bitable records and even suggests unattended execution, but it does not require an explicit warning or confirmation before modifying user data. In this context, the combination of automation, pagination, and background execution increases the risk of large-scale accidental or incorrect updates if the skill is invoked mistakenly or the matching logic is imperfect.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal