ClawHub
Back to skill

Security audit

Gmail (tc)

Security checks for vulnerabilities and agentic risk

Overview

This Gmail skill does what it says, but it handles private mailbox access and real email-sending authority that users should treat carefully.

Install only if you intend to let the agent access the configured Gmail account. Store the OAuth client secret and refresh token securely, grant the narrowest Gmail scopes that fit your use case, and verify recipients, attachments, drafts, and label changes before allowing send or modify operations.

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
93% confidence
Finding

The skill requires highly sensitive OAuth credentials and a Gmail refresh token that can provide ongoing mailbox access, but the description does not explicitly warn users about the sensitivity of these secrets or the breadth of mailbox data exposed. This increases the risk of unsafe deployment, accidental secret sharing, or use in contexts where users do not fully understand the privacy implications.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill can send emails externally and modify mailbox state through labels, threads, and drafts, yet it does not clearly warn that these actions can change user data and trigger real-world communications. Without explicit disclosure, users may invoke the skill without appreciating that it can perform irreversible or sensitive actions on their behalf.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.