ClawHub
Back to skill

Security audit

Gws Gmail Forward

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused Gmail forwarding helper with clear command usage, but users should confirm recipients and attachment handling before sending.

Before installing or using this skill, make sure the gws Gmail account is the one you intend to use, verify the recipient list carefully, and use --draft or --dry-run for sensitive messages. Original attachments are included by default unless --no-original-attachments is used.

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
95% confidence
Finding
The skill documents a command that can immediately forward an existing email, including original attachments by default, to new recipients, but it does not prominently warn about the exfiltration and misdelivery risk. In an agent-driven context, this omission is dangerous because a user or automated workflow may trigger forwarding without realizing sensitive message contents and attachments will be sent externally unless draft or dry-run modes are used.

Static analysis

No suspicious patterns detected.