ClawHub

Notion 想法点子库 + 里程碑追踪

Security checks across malware telemetry and agentic risk

Overview

This Notion skill is a disclosed helper for reading and writing Notion records, with user confirmation before its bundled write scripts mutate data.

Install only if you intend to connect this agent to Notion. Use a dedicated least-privilege Notion integration token, protect ~/.config/notion/api_key, confirm the hard-coded database IDs match your workspace, and read confirmation prompts carefully before approving writes.

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
81% confidence
Finding
Broad trigger phrases like '这是个好想法' can overlap with ordinary conversation and may unintentionally initiate a write-oriented workflow. In a persistence skill connected to an external SaaS, accidental activation can cause unintended storage of user content or metadata in Notion.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The update-status table includes vague natural-language phrases such as '进行中' or '不要了' that are common in everyday conversation and could map to destructive or state-changing actions. This raises the risk of unintended record modification or archival in the connected Notion workspace.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal