ClawHub
Back to skill

Security audit

Second Brain

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Notion capture helper, with some accidental-save risk from broad activation words.

Install only if you want short Telegram-style messages containing capture terms to be saved into your Notion Second Brain. Review the activation words and make sure the Notion integration is shared only with the intended Second Brain page, because low-confidence captures may still be written without a clarification step.

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
  • 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
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description states that the skill files incoming Telegram messages into Notion, but it does not clearly constrain when that behavior should activate beyond loose keywords and patterns. In context, this ambiguity is more dangerous because the skill explicitly avoids clarifying questions and performs persistent writes, increasing the chance that routine chat messages are interpreted as commands and stored in the user's workspace.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation keywords include very broad, everyday terms like "note," "book," "remember," and "inbox," which can cause the skill to trigger on ordinary conversation that was not intended for Notion capture. Because the skill is designed to write directly into the user's Notion workspace without clarifying questions, accidental activation can lead to unintended data creation, misfiled content, and privacy issues from storing messages the user did not mean to persist.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.