ClawHub
Back to skill

Security audit

Osop Report

Security checks across malware telemetry and agentic risk

Overview

This skill is a local OSOP report generator that reads selected workflow/log files and writes an HTML report, with ordinary privacy cautions for generated reports.

Install if you are comfortable letting the skill read the OSOP files you provide and create a local HTML copy of their contents. Review generated reports before sharing them, especially when logs may include prompts, outputs, reasoning, errors, costs, or operational metadata.

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
95% confidence
Finding
The skill reads user-supplied files and writes a generated HTML report, but it declares no explicit permissions for file access. This creates a transparency and least-privilege problem: users or policy systems cannot accurately assess or constrain the skill's filesystem capabilities, increasing the risk of unintended file access or overwriting files in the working environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.