Security audit

Zoho Mail CLI

Security checks for vulnerabilities and agentic risk

Overview

This Zoho Mail skill is coherent, but it asks users to install an unpinned third-party mail CLI that handles OAuth tokens and also documents irreversible mail deletion without enough safety guidance.

Review the upstream zoho-cli source and installation path before installing. Prefer a pinned release or commit with integrity verification, and be careful granting OAuth access because the tool can read, send, download, move, and delete mail. Avoid using permanent delete or folder delete through automation unless you have independently confirmed exactly what will be affected and have recovery options.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (1)

T08 · Insecure Dependencies

Error

Location: SKILL.md:22
Finding: Unpinned Third-Party CLI Installation from Mutable Sources
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill documents destructive actions such as permanent deletion of mail and folder deletion without prominent safety guidance, confirmation requirements, or warnings about irreversible consequences. In an agent-oriented context, these commands may be invoked programmatically from search results or automation pipelines, increasing the chance of accidental bulk data loss.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.