ClawHub
Back to skill

Security audit

Capture Classification

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: classifies captured notes or transcripts and routes them to Google Tasks or vector memory, with no hidden code or install-time behavior found.

Install this only if you want captured notes or transcripts automatically classified and routed into Google Tasks or vector memory. Avoid using it on content that contains secrets, regulated data, or private material unless those destinations are approved for that data.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill automatically routes captured unstructured text into external systems (Google Tasks or a vector store) without any user-facing notice, consent step, or data sensitivity check. Because captured notes/transcripts can contain personal, confidential, or regulated information, silent transmission and storage increases the risk of privacy leaks, unintended retention, and compliance violations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

The natural-language instructions prominently impose Japanese terminology and framing such as 'Kaizen', 'Hyojun Sagyo', and 'Jidoka' as part of the operating procedure. While not severe, this introduces a locale/language preference without any opt-in or alternative phrasing for users who may not want region-specific terminology.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.