ClawHub

Didit Proof Of Address

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Didit proof-of-address helper, but it uploads sensitive address documents to Didit and uses the user's API key.

Install only if you intend to use Didit for proof-of-address checks. Use a Didit API key you are comfortable exposing to this workflow, confirm the exact document before upload, avoid unnecessary vendor_data, and review Didit's privacy, retention, and billing behavior before submitting utility bills, bank statements, or government documents.

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
94% confidence
Finding
The documentation explains how to upload proof-of-address documents to Didit but does not prominently warn users that highly sensitive personal documents and extracted address/name data are sent to an external verification provider. This is a real privacy and consent issue, especially because PoA files can contain addresses, full names, account details, and other regulated personal information. The skill context makes this more dangerous, not less, because external transmission is core to the workflow and involves KYC-grade data.

Missing User Warnings

Medium
Confidence
78% confidence
Finding
The script transmits highly sensitive proof-of-address documents and optional vendor identifiers to a third-party service without any explicit runtime warning, confirmation, or privacy notice to the user. In a skill that handles personal documents, silent transmission increases the risk of accidental disclosure, policy noncompliance, and misuse in contexts where the operator did not realize data would leave the local environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal