ClawHub
Back to skill

Security audit

Persona Researcher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed research persona that uses Google Workspace tools for organizing notes and collaboration, with email-sharing risk users should supervise.

Install only if you are comfortable giving the agent Google Workspace capabilities for research files and collaboration. Before allowing it to send Gmail messages or announce files, confirm recipients, shared links, and whether notes, drafts, datasets, or internal documents contain sensitive information.

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 (1)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill explicitly instructs sending email to collaborators via Gmail but does not require confirming recipients, reviewing attachments, or warning the user that research data may be shared externally. In a collaboration-oriented persona, this increases the chance of accidental disclosure of sensitive notes, datasets, drafts, or internal links through normal use rather than overt exploitation.

Static analysis

No suspicious patterns detected.