ClawHub

Easydoc Mask

Security checks across malware telemetry and agentic risk

Overview

The skill appears to do what it claims: send user-chosen medical documents to EasyLink for redaction, which is sensitive but disclosed and purpose-aligned.

Install only if you are authorized to send the documents to EasyLink's remote service. Treat uploaded files and saved results as sensitive medical data, confirm vendor/compliance approval for your jurisdiction, and avoid using this on regulated records unless your organization permits that processing.

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 (7)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This skill is designed to upload EMR and other potentially sensitive medical documents to a third-party API, yet it does not require an explicit warning or consent step before transmission. In the medical context, that is especially dangerous because users may unknowingly send regulated health information off-system, creating privacy, compliance, and data handling risks.

Natural-Language Policy Violations

Medium
Confidence
83% confidence
Finding
The skill hardcodes a single CN-hosted platform without user choice or justification, which can create jurisdiction, residency, and compliance issues when handling medical records. In a healthcare data flow, silently forcing cross-border or region-specific processing materially increases risk for users who assume local handling requirements are being met.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The document instructs users to upload EMR and other potentially highly sensitive medical records to a third-party remote API, but it does not warn about privacy, regulatory, consent, retention, or cross-border data handling implications. In a healthcare context, omission of these safeguards can lead to unauthorized disclosure of PHI/PII and noncompliance with legal obligations even if the API itself is legitimate.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script uploads local files, including EMR/documents, to a third-party API endpoint by design, but it does so without any explicit user-facing notice at the point of submission that the file contents leave the local system. In this skill context, the files are likely highly sensitive medical records, so lack of a clear transmission warning can lead to accidental disclosure to an external service by users who may assume processing is local.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The script can save API responses to a local file without warning that the output may still contain sensitive metadata, task identifiers, URLs, or partially sensitive masking results. While this is less severe than the upload itself, it can cause inadvertent persistence of sensitive information on disk in shared or insecure environments.

External Transmission

Medium
Category
Data Exfiltration
Content
Submit with default masking:

```bash
curl -X POST "https://api.easylink-ai.com/v1/easydoc/mask" \
  -H "api-key: your_apikey_here" \
  -F "files=@record.pdf" \
  -F "mode=emr-mask"
Confidence
92% confidence
Finding
https://api.easylink-ai.com/

External Transmission

Medium
Category
Data Exfiltration
Content
Submit with custom fields:

```bash
curl -X POST "https://api.easylink-ai.com/v1/easydoc/mask" \
  -H "api-key: your_apikey_here" \
  -F "files=@record.pdf" \
  -F "mode=emr-mask" \
Confidence
92% confidence
Finding
https://api.easylink-ai.com/

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal