ClawHub
Back to skill

Security audit

nexus-talent-assessor

Security checks for vulnerabilities and agentic risk

Overview

This HR assessment skill is coherent, but it requests broad file and web access for sensitive employee-related work without explaining limits or consent controls.

Install only if you are comfortable granting this skill access to local files and web tools for HR assessment work. Before use, define which employee records it may read, avoid unnecessary sensitive data, and require explicit approval before any HR content is used with external web sources or citations.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 explicitly declares both web-fetch/web-search and filesystem access, but the manifest provides no notice about what local data may be read, what remote destinations may be contacted, or how sensitive HR-related information is handled. In an HR talent assessment context, this is more dangerous because the agent may process employee evaluations, 360-feedback, and career data, creating a meaningful risk of unintended data exposure or transmission.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.