ClawHub
Back to skill

Security audit

Contact Centre Grok Pack

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local transcript triage helper whose file reading and optional JSON output are disclosed and aligned with its stated purpose.

Use this with the same care as the original call transcripts. Avoid writing output files on shared systems unless needed, store results where customer data is permitted, and review the JSON before sending anything into CRM or helpdesk systems.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill documentation describes running a local script that reads transcript input and can write JSON output, but the manifest declares no explicit tool scope or permissions. This creates a mismatch between declared capabilities and actual behavior, which can lead to over-broad execution assumptions, weak policy enforcement, or unsafe deployment in environments that rely on manifest-level restrictions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The script can persist classification output to a user-specified file, and that output includes a summary derived directly from the transcript plus routing evidence. In a contact-centre context, transcripts can contain sensitive personal, medical, financial, or safeguarding information, so silently writing this data to disk creates a real confidentiality and data-retention risk, especially on shared systems or when operators assume processing is ephemeral.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.