ClawHub
Back to skill

Security audit

巨量广告自动化投放技能 - LemClaw Skills

Security checks across malware telemetry and agentic risk

Overview

This ad automation skill mostly matches its purpose, but it can launch paid ads with live credentials and includes weak safeguards around spend and credential storage.

Install only if you intend to let an agent operate an Ocean Engine advertising account. Use test mode first, provide least-privilege or limited-scope credentials where possible, set external budget limits in the ad platform, avoid calling save_config() with production secrets, and require manual review before live launch, batch launch, budget, bid, or creative changes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documents and encourages capabilities that access environment variables, execute local Python commands, and perform outbound network operations, but it declares no permissions. This creates a transparency and governance gap: users or hosting platforms cannot accurately assess that the skill may read API secrets and make live advertising API calls that can change spend or exfiltrate sensitive account data.

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The module writes full sensitive credential material, including access token, refresh token, and app secret, into a local config.json file in plaintext. If the working directory is accessible to other users, included in backups, committed to source control, or exposed by another component, these secrets can be stolen and used to access or refresh the advertising account.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.