ClawHub
Back to skill

Security audit

worklittle-jobs-mcp

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly coherent for a remote jobs service, but it enables paid job applications and account or ATS changes without clearly requiring review and confirmation first.

Review API-key scopes before installing. Use this skill only when you are comfortable sending job-search, resume, cover-letter, and account or ATS data to Worklittle, and require your agent to ask for explicit confirmation before submitting applications, spending per-application fees, or changing company, job-listing, candidate, note, bookmark, or pipeline data.

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 (3)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill promotes resume and cover-letter generation through a remote MCP service but does not clearly warn that sensitive career data, employment history, education, and possibly contact details will be transmitted to an external service. This is a genuine privacy and data-handling issue because users may disclose highly sensitive professional information without informed consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly guides an agent from job search to `submit_job_application` without requiring a confirmation step, even though the action is user-affecting and incurs a per-submit charge. In an agentic workflow, this creates a real risk of unintended paid submissions, accidental applications to the wrong jobs, or bulk misuse if a prompt is ambiguous or the agent is over-eager.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The skill describes account connection and remote profile-management capabilities such as `set_company` without clearly warning that these actions can modify data in the user's external Worklittle account. While expected for this kind of integration, the lack of explicit notice can still lead to unintended account changes if an agent acts without adequate user awareness.

Static analysis

No suspicious patterns detected.