ClawHub
Back to skill

Security audit

Remote Job Hunter

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a job-search automation skill with expected email/reporting behavior, but users should be aware it may use configured SMTP credentials for outbound reports.

Install only if you want automated job-search reports and are comfortable configuring SMTP email sending. Review any schedule or daily-run setup, confirm before first outbound email, and use a dedicated email/app password if possible.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases are broad enough to match many ordinary employment-related requests, which can cause the skill to activate in contexts the user did not specifically intend. In an agentic environment, over-broad activation increases the chance of unnecessary execution of job-search workflows and exposure of configured data such as profile or email settings.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The usage guidance repeats ambiguous activation criteria without defining boundaries for when the skill should not run. This can lead the agent to invoke the skill for loosely related user requests, increasing the risk of unintended automation, configuration access, or downstream email/reporting behavior.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation describes a full pipeline that can send email reports but does not prominently warn that stored SMTP credentials may be used during daily runs. This creates a risk that an agent or user triggers outbound email unexpectedly, potentially exposing personal data, consuming third-party accounts, or causing unauthorized communications.

Static analysis

No suspicious patterns detected.