ClawHub
Back to skill

Security audit

Dpdp Checklist Gen

Security checks across malware telemetry and agentic risk

Overview

The skill appears to use a declared third-party API, but it may send sensitive compliance details without clear user consent or data-minimization guidance.

Install only if you are comfortable sending the information you provide to the ToolWeb service. Avoid entering regulated, customer, employee, health, children-related, or confidential business details unless you have approval, and use a scoped or revocable API key where possible.

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
95% confidence
Finding
The skill instructs the agent to collect detailed organizational and data-processing context and transmit it to a third-party API, but it does not require explicit user notice, consent, or data-minimization before sending. Because the content includes potentially sensitive compliance, employee, customer, health, or children-related processing details, this creates a real confidentiality and privacy risk even if the API is legitimate.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill declares dependence on TOOLWEB_API_KEY and directs use of that credential in outbound requests without any guidance on safe handling, scoping, storage, or non-disclosure. This is a weaker issue than direct exfiltration, but it still increases the chance of credential misuse, accidental exposure, or overly broad trust in a third-party service.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.