ClawHub
Back to skill

Security audit

Proof Card Forge

Security checks across malware telemetry and agentic risk

Overview

This skill is a small, user-run generator for proof-card SVG, Markdown, and JSON files, with no evidence of hidden or harmful behavior.

Reasonable to install if you want to generate proof-card assets. Run it on audit files you trust, review the generated score/status/link before publishing, and be careful with --force because it permits overwriting existing output files.

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
81% confidence
Finding
The skill advertises no declared permissions, yet its documented workflow and metadata indicate capabilities to read audit files, write SVG/Markdown/JSON artifacts, and potentially access network resources via homepage/provenance references. This mismatch weakens policy enforcement and user understanding: an agent or platform may allow execution under an under-declared trust model, increasing the chance of unintended file access or outbound access.

VirusTotal

54/54 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.