ClawHub
Back to skill

Security audit

LYGO Champion: arkos celestial architect

Security checks across malware telemetry and agentic risk

Overview

This is a deprecated persona-helper skill whose local reference reads and hash-check scripts are disclosed and limited to its own packaged files.

Safe to install if you want this legacy persona, though new users should consider the named successor skill instead. Only run the external verifier or successor install command if you trust that separate package and want its ledger or migration behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill appears to rely on file-reading behavior without declaring corresponding permissions, which creates a transparency and policy-enforcement gap. Even if the reads are limited to local reference files, undeclared capabilities can surprise users and bypass expected review boundaries, especially in agent frameworks that use manifest permissions for trust decisions.

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding
The file presents itself as a deprecated persona/helper slug, but the detected behavior includes reading repository files, validating content, and printing a hash from canon.json. This mismatch is dangerous because users and reviewers may grant trust based on the harmless description while the skill performs additional data-access and validation actions that were not clearly disclosed.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.