Back to skill

Security audit

Stainless Client Tracker

Security checks for vulnerabilities and agentic risk

Overview

This CRM skill is coherent, but it describes automatic sharing and messaging of customer data without clear consent or approval controls.

Before installing or using this skill, confirm that any Feishu sync, WeChat greeting, email quote/contract, or calendar action requires explicit user approval and only sends the minimum necessary customer data to authorized recipients.

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
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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises automatic synchronization to Feishu plus automatic outbound messaging over WeChat and email, but provides no notice about user consent, recipient consent, data minimization, or privacy boundaries. In a CRM-style skill handling customer identities, contact details, schedules, and commercial data, this can lead to unauthorized disclosure of personal or business information and non-compliant messaging behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The file forces a single language presentation throughout the skill documentation, and there is no indication that users can opt into another language or that the skill is intentionally restricted to a Chinese-speaking region. Under the policy criteria, a fixed language without user choice can constitute a natural-language policy violation.

Content

No source excerpt is available for this finding.