ClawHub
Back to skill

Security audit

packing-pro

Security checks across malware telemetry and agentic risk

Overview

This is a local packing-list generator with one disclosed option to save output to a user-chosen file.

Installers should treat this as a benign local utility. Use the --output option only with a path you intend to create or replace, since the script writes directly to that path. No evidence was found of hidden network calls, credential use, background persistence, destructive behavior, or unrelated system access.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill advertises file-writing capability via the `--output` option and default behavior, but the metadata declares no permissions. This creates a permission-model mismatch: an agent or user may invoke the skill expecting it to be read-only, while it can persist data to disk and potentially overwrite files if path handling is not constrained.

VirusTotal

50/50 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.