Security audit

Job Auto Apply

Security checks for vulnerabilities and agentic risk

Overview

This skill is not clearly malicious, but it needs Review because it automates real job applications while handling sensitive applicant data and includes under-scoped external sharing and anti-bot bypass guidance.

Review carefully before installing. Keep dry-run and per-application confirmation enabled, avoid CAPTCHA/proxy bypass workflows, do not grant unnecessary social-posting permissions, verify the install slug, and assume resume/profile/job data may be sent to external AI services.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (10)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill clearly describes capabilities that require network access, reading environment variables, and writing files, yet it declares no permissions. This creates a dangerous trust gap: a user or host system may authorize the skill under the assumption it is low-privilege, while it can handle sensitive profile data, API keys, and outbound submissions to third parties.

Context-Inappropriate Capability

Medium

Confidence: 97% confidence
Finding: The document explicitly recommends CAPTCHA-solving services and anti-blocking tactics in the context of automated job applications. These capabilities go beyond ordinary job-search automation and enable bypass of platform abuse-prevention controls, increasing the likelihood of terms-of-service violations and unauthorized automation.

Context-Inappropriate Capability

Medium

Confidence: 93% confidence
Finding: The resume-tailoring example sends the user's full resume text and a job description to an external API. That creates unnecessary exposure of sensitive personal and professional data to a third party without clear minimization, consent, or disclosure controls in the skill documentation.

Context-Inappropriate Capability

Medium

Confidence: 96% confidence
Finding: Troubleshooting advice to use residential proxies is a direct recommendation to evade platform detection and access controls. In an auto-apply skill, this makes the behavior more dangerous because it facilitates scaling and concealment of automated actions that platforms may explicitly restrict.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The activation phrases are broad enough that ordinary requests like 'help me apply to multiple jobs automatically' or similar variants could trigger a high-impact automation workflow. In this skill's context, accidental activation is more dangerous than usual because it can search external sites, generate application materials, and potentially submit real applications using sensitive personal data.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill handles resumes, contact details, work authorization, and likely other sensitive applicant data, and sends information to external job platforms and SkillBoss API Hub, but this is not prominently disclosed as a data-transfer/privacy warning. Users may unknowingly expose personal and employment-related information to multiple third parties, including AI services used for cover letters and screening-question assistance.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The compatibility-analysis flow sends applicant-identifying information and job content to an external API without explicit user consent or a clear privacy notice. In a job-application skill, this context increases sensitivity because resumes, experience, and employment preferences are personal data that users may not expect to leave the local workflow.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: Cover-letter generation transmits applicant details and job information to a third-party API without an explicit warning or consent step. Because this skill handles real employment materials, unintended external sharing can expose sensitive personal and professional information.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The markdown describes sending resumes, profile details, company research, and job-related content to an external API but does not provide a clear user-facing warning about privacy implications. Because job applications involve highly sensitive personal data, omission of notice and consent materially increases privacy and compliance risk.

Natural-Language Policy Violations

Medium

Confidence: 98% confidence
Finding: The guidance to use CAPTCHA-solving services promotes bypass of platform protective measures without any policy justification or user-consent guardrail. That is dangerous because it normalizes covert circumvention behavior in a workflow that already automates sensitive, account-linked actions.

Static analysis

No suspicious patterns detected.