ClawHub

Hekkova Openclaw Skill

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Hekkova MCP skill for permanently minting selected content, URLs, and metadata to blockchain/IPFS-backed storage, with real privacy tradeoffs but no hidden executable payload.

Install only if you are comfortable with an agent sending selected content or URLs to Hekkova for durable storage. Treat minting and full_moon phase changes as publication actions: review sensitive data, consent, copyright, and credit costs first. Keep HEKKOVA_API_KEY private and consider requiring manual approval for mint_moment, mint_from_url, and update_phase to full_moon.

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
90% confidence
Finding
The README advertises `mint_from_url` as a server-side fetch capability but does not clearly warn users that the target URL, fetched content, and related metadata will be transmitted to Hekkova's backend for retrieval and processing. In a privacy-focused skill handling potentially sensitive memories, this omission can mislead users into sending private or regulated content through a third-party service without informed consent.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The README emphasizes permanence and blockchain/IPFS storage but does not plainly warn that minting is effectively irreversible and may place recoverable artifacts or metadata onto public decentralized infrastructure. For an agent skill that can preserve user-supplied text, media, and web content, lack of a clear irreversible-action warning increases the chance of accidental disclosure or permanent publication of sensitive information.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill enables permanent minting to blockchain/IPFS and notes that `full_moon` content is fully public, but it does not present a prominent, explicit user warning at the action point that publication may be irreversible and globally accessible. In an agent setting, a user may ask to mint sensitive content without understanding that once exposed publicly or anchored permanently, later deletion or privacy changes may not fully retract disclosure.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal