ClawHub

Docuseal

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent DocuSeal CLI reference, but it can upload documents, contact real recipients, and change signing records when used with a DocuSeal API key.

Install only if you want an agent to operate your DocuSeal account. Use a limited, revocable API key if possible, verify `DOCUSEAL_SERVER`, and require explicit approval before commands that upload confidential documents, email or SMS recipients, enable shared links, archive records, update contact details, or mark signing as completed.

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
89% confidence
Finding
The skill instructs agents to create templates, send documents for signing, and email submitters via a third-party service, but it does not explicitly warn that document contents, signer identities, email addresses, and related metadata will be transmitted to DocuSeal. In an agent setting, that omission can lead to unintentional disclosure of sensitive or regulated data because the user may not realize an external service is involved or what data leaves the local environment.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation presents high-impact state-changing options such as `--completed` (auto-signed), `--send-email`, and `--send-sms` without any warning about their irreversible or user-impacting consequences. In a CLI/automation skill used in shells and CI/CD, this increases the risk of operators or automated workflows unintentionally marking documents complete or triggering external notifications, potentially causing compliance, audit, or customer-trust issues.

Missing User Warnings

Medium
Confidence
77% confidence
Finding
The documentation encourages ingestion of local files, remote URLs, inline HTML, and base64 content without any warning about sensitive-data handling, trust boundaries, or risks of fetching remote content. In a CLI/CI context, this can lead users to upload confidential documents or cause the backend to retrieve attacker-controlled URLs, increasing the chance of data leakage, inadvertent exposure, or server-side request abuse depending on backend behavior.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal