ClawHub
Back to skill

Security audit

Gmail Local

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently provides local Gmail read/search/send access and includes proportionate safeguards for credentials and sending mail.

Install only if you are comfortable giving the skill direct IMAP/SMTP access to the configured Gmail account. Use a dedicated app password, keep the credential file owner-only readable, rotate or revoke the app password when no longer needed, and approve sends only after reviewing recipients and message content.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill requires access to environment variables and a local credential file, but it does not declare an explicit tool/permission scope such as allowed-tools or permissions. That omission weakens least-privilege controls and makes it harder for a host system to constrain what the skill may access, especially since the skill handles live email credentials and mailbox contents.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 89)May include surrounding context.

md
- The helper refuses to send unless `--confirm-send` is provided after that
  approval.
- Do not use this skill to mass-mail, spam, scrape contacts, or send sensitive
  data without confirmation.
- Prefer read-only commands (`list`, `search`, `read`) unless the user clearly
  asks to send.
- If an authentication error occurs, do not retry repeatedly; ask the user to

Session Persistence

Medium
Category
Rogue Agent
Confidence
83% confidence
Finding

The skill instructs users to persist a Gmail App Password in a local file for ongoing reuse. Although it recommends 0600 permissions, this is still long-lived credential storage for a high-value mailbox token, and compromise of the host or misconfiguration of the file path would expose direct IMAP/SMTP access.

Content

Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.

Setup

Create a Google App Password at:

text
https://myaccount.google.com/apppasswords

Static analysis

No suspicious patterns detected.