ClawHub
Back to skill

Security audit

Client Flow

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed client-onboarding automation that can affect files, email, calendar, task tools, and stored client records, but those capabilities match its stated purpose.

Install only if you want an agent to manage client onboarding records and draft or create related operational items. Before enabling Gmail, Google Calendar, cloud storage, or task-manager integrations, confirm where client data will be stored and review any email, event, task-board, or reminder before it is created externally.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description emphasizes convenience but does not prominently warn that the skill may create local or cloud files, send or draft emails, schedule calendar events, create task board entries, store client information, and update registries. Because the skill handles external side effects and potentially sensitive client data, weak disclosure raises the risk of unintended data propagation, privacy issues, and unauthorized operational changes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises very broad trigger phrases such as general project setup and status-check requests, which increases the chance it will activate in routine conversation without the user intending to launch a multi-step automation. In this context, accidental invocation is more dangerous because the skill can create folders, draft or send emails, schedule meetings, and modify task systems using client data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.