ClawHub
Back to skill

Security audit

Zoho Bigin CRM

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Zoho Bigin CRM helper with expected credential use and write guardrails, though its generic trigger words could cause accidental activation.

Install this only if you intend Codex to work with Zoho Bigin CRM data. Be careful with generic requests involving contacts, accounts, deals, or notes, and require clear confirmation before any command that creates, updates, moves, or deletes records.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list is broad enough to match generic terms like "CRM," "Deal," "Contact," and "Account," which can cause the skill to activate for requests not specifically intended for Zoho Bigin. Because this skill supports write operations against CRM records, unintended invocation could expose sensitive business data or increase the chance of an accidental record modification if the agent routes a request here incorrectly.

Static analysis

No suspicious patterns detected.