ClawHub

Publish Guard

Security checks across malware telemetry and agentic risk

Overview

Publish Guard is a local pre-release audit tool whose repo scanning and secret-pattern checks match its stated purpose.

Install if you want a local publish-readiness audit. Run it against a specific repo rather than your home directory or filesystem root, and treat generated reports as sensitive because they can contain filenames and line numbers for secret findings even when snippets are redacted.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Credential Access

High
Category
Privilege Escalation
Content
from pathlib import Path
TEXT_EXTENSIONS = {
    ".cer",
    ".env",
    ".ini",
    ".js",
    ".json",
Confidence
60% confidence
Finding
.env"

Credential Access

High
Category
Privilege Escalation
Content
return True
    if lower_name in TRACKED_TEXT_FILENAMES:
        return True
    return lower_name == ".env" or lower_name.startswith(".env.")


def under_size_limit(path: Path) -> bool:
Confidence
60% confidence
Finding
.env"

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal