Security audit

Zoho Desk

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Zoho Desk integration, but it asks users to enable an unpinned third-party plugin that handles OAuth-backed support data and write actions.

Install only if you trust ClawLink and the ClawHub plugin source to handle Zoho Desk OAuth and support data. Use the least-privileged Zoho account available, review OAuth scopes during connection, and confirm write actions carefully, especially bulk task updates and department-logo changes.

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

Warning

Location: SKILL.md:30
Finding: Unpinned Third-Party Plugin Receives Access to Sensitive Zoho Desk Data
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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

Findings (1)

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: Line L058 says write operations are 'create ticket, update tasks,' which omits the documented write capability to upload/update department logos and frames task updates as the representative write action. This is an intent/documentation inconsistency within the skill file rather than a code-level contradiction, but it still misstates what the skill actually allows users to modify.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.