ClawHub
Back to skill

Security audit

Social Recruit Page

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a disclosed poster generator with optional Feishu delivery, but Feishu credentials should be handled carefully.

Install this only if you want a tool that can generate a recruitment image and, when requested, send it to Feishu. Avoid putting app secrets directly in shell history when possible, confirm the recipient ID before sending, use a least-privileged Feishu app, and do not allow access to local OpenClaw credentials unless you intend to use them for Feishu delivery.

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 (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README instructs users to pass Feishu recipient identifiers and app credentials on the command line and send content over the network, but it does not warn that these values will be transmitted to external services and may also be exposed locally via shell history or process listings. In a skill that generates promotional material for direct delivery, this omission makes accidental credential mishandling and unintended data disclosure more likely.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation states that Feishu credentials may be read from a local config file, but it provides no warning that the skill will access sensitive local secrets and use them for outbound API calls. This is dangerous because users may not realize the skill can consume stored credentials automatically, enabling unintended message sending or secret exposure if the environment is shared or misconfigured.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation explicitly supports sending generated images to Feishu and states that credentials may be read from a local config file, but it does not mention user consent, destination verification, or safeguards around secret handling. In an agent skill context, this creates a real risk of unintended external data transmission and implicit use of locally stored credentials without the operator clearly understanding that the skill may access them.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.