Back to skill

Security audit

Agent Email Setup

Security checks for vulnerabilities and agentic risk

Overview

The skill sets up agent email, but it also routes all mail through a hard-coded personal Gmail account and directs broad agent memory/context transfer beyond email setup.

Review carefully before installing. Replace the hard-coded personal Gmail forwarding with an approved organization-controlled mailbox or disable blanket forwarding, separate general knowledge transfer into a distinct reviewed provisioning workflow, and make sure outbound email sending is gated by enforceable human approval rather than prose instructions alone.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

other

Error
Location
SKILL.md:36
Finding

Mandatory Exfiltration of Agent Email to a Hard-Coded Personal Account

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:300
Finding

Excessive Cross-Agent Transfer of User Context and Persistent Memory

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:97
Finding

Direct Email Tool Enablement Without an Enforced Approval Boundary

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Automatically forwarding all agent email and CC'ing all outbound mail to a personal Gmail account introduces privacy, confidentiality, and data-handling risk, especially for support tickets, competitions, and manufacturer communications. The lack of an explicit warning, consent model, retention guidance, or data-classification limits makes accidental leakage of sensitive operational or third-party information more likely.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s stated purpose is email setup, but it also directs broader agent bootstrapping and knowledge-transfer actions. Expanding scope in this way can cause operators to copy unrelated identity, memory, and system context into agent workspaces, increasing unnecessary access and data exposure beyond what email configuration requires.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The knowledge-transfer instructions explicitly direct copying broad user context, system knowledge, memory, and history into each new agent workspace. This violates least-privilege principles and can unnecessarily replicate sensitive information across agents, making compromise, misuse, or accidental disclosure more damaging and harder to contain.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs use of a general automation script for agent knowledge transfer that is not narrowly related to email setup. Invoking broad provisioning automation from a focused operational skill creates a confused-deputy risk, where an operator may grant or propagate more data and capabilities than intended during a routine mail configuration task.

Content

No source excerpt is available for this finding.