ClawHub
Back to skill

Security audit

Bangai Recruit

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow recruiting-platform guide that handles applicant data and candidate decisions, but those actions are disclosed, purpose-aligned, and not backed by hidden code or persistence.

Install only if you intend the agent to help operate a logged-in Bang.AI recruiting account. Review candidate details before any approve/reject action, avoid unnecessary copying or sharing of applicant information, and treat candidate data as sensitive personal information subject to your organization’s hiring and retention policies.

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
  • 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
Confidence
95% confidence
Finding
The skill describes access to candidate lists and detailed profiles containing personal and potentially sensitive employment data, but provides no privacy or data-handling warning. This omission can normalize broad access, disclosure, or unnecessary processing of applicant information in a way that increases privacy and compliance risk.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs users to approve or reject candidates but does not warn that these actions modify real applicant records and can directly affect people’s hiring outcomes. In an agent setting, omission of this consequence increases the chance of accidental or overly broad bulk actions, especially because the skill frames the workflow as routine platform operation.

Static analysis

No suspicious patterns detected.