ClawHub
Back to skill

Security audit

Job Search Agent

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent as a job-search assistant, but its bulk auto-apply feature can send sensitive application data without clear review, consent, or data-handling limits.

Review this skill carefully before installing. It may be useful for job searching, but only use auto-apply with explicit review of each employer, role, cover letter, CV, and submitted personal details. Avoid giving it access to job-board accounts or sensitive profile data unless you are comfortable with how those applications will be sent and tracked.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The CV matching and auto-apply features imply collection and processing of sensitive personal data such as CV contents, employment history, skills, and possibly contact details, yet the skill provides no privacy notice or handling constraints. Because this skill is specifically designed to process and transmit employment-related data across multiple external platforms, the omission increases the risk of oversharing, unauthorized retention, or sending personal information to unintended recipients.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises an auto-apply capability that can submit job applications on the user's behalf, but it provides no warning about consent, review, rate limiting, or the risks of mass submission. In a job-search context, this can lead to unintended applications, disclosure of personal data to third parties, and reputational harm if inaccurate or low-quality submissions are sent automatically.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.