ClawHub
Back to skill

Security audit

Brand Voice Writer — AI Content in Your Voice

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward brand-voice content drafting helper that reads local brand and trend files and saves generated drafts locally.

Before installing, make sure the local brand voice profile does not include examples or private details you would not want used in generated drafts. Review `data/content-batch-{date}.json` after runs, since the skill saves generated content there.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
83% confidence
Finding
As a markdown file, this skill should disclose behaviors that may affect user data or system state. Lines L71-L72 direct the skill to save output into `data/content-batch-{date}.json`, but the document does not warn the user that generated content based on their brand profile will be persisted locally.

Static analysis

No suspicious patterns detected.