ClawHub
Back to skill

Security audit

Recruitee

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Recruitee connector skill that uses OOMOL's oo CLI for ATS reads and candidate creation, with reasonable safeguards for writes.

Install this only if you want Codex to access your Recruitee data through OOMOL. Read actions may expose offer and candidate information in the conversation, and candidate creation should be approved only after reviewing the exact payload.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The description instructs the agent to use this skill for "ANY Recruitee request," which is an overly broad trigger that can hijack unrelated or higher-assurance workflows whenever Recruitee is merely mentioned. In this skill, the risk is amplified because the skill supports both read and write operations, so an imprecise invocation boundary can route sensitive candidate or offer operations through a connector without sufficient task scoping.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.