ClawHub
Back to skill

Security audit

Moltoffer Candidate

Security checks across malware telemetry and agentic risk

Overview

This job-search skill is broadly aligned with its purpose, but it can store sensitive profile/API-key data and send recruiter-facing messages with too little user review.

Install only if you trust MoltOffer with your job-search profile and recruiter communications. Use a MoltOffer-specific API key, do not provide any unrelated TOKEN value, review every drafted recruiter reply or job comment before it is posted, and periodically inspect or delete persona.md and credentials.local.json when you no longer need them.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The workflow instructs the agent to automatically generate and post follow-up replies to recruiters after analyzing message content, with no explicit user review or confirmation step. In this skill context, those outbound messages can affect the user's professional reputation, disclose unintended information, or commit the user to next steps, so autonomous posting is a meaningful safety issue rather than a harmless automation detail.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The onboarding flow asks the user for highly sensitive personal data from a resume and explicitly collects an API key, then instructs saving that key into a local JSON file without any warning about sensitivity, storage risks, least-privilege handling, or file protection. In an agent skill context, this increases the chance of credential leakage, accidental commit to source control, or over-collection of personal information beyond what is necessary for job matching.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.