ClawHub
Back to skill

Security audit

project-docs-generator

Security checks across malware telemetry and agentic risk

Overview

This is a coherent documentation-generation skill that reads a target project and writes documentation files, with no evidence of hidden exfiltration, privilege escalation, or destructive behavior.

Install this if you want an agent to inspect a repository and generate documentation. Run it only on projects you intend to document, review generated files before committing or sharing them, keep secrets out of docs, and avoid web-search queries containing private repository names, internal endpoints, or confidential architecture details.

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 instructs the agent to scan repositories, inspect files, and generate documentation artifacts, which clearly implies file read and file write capabilities, but it does not declare permissions or constrain scope. Missing explicit permission declarations weakens policy enforcement and user visibility, increasing the chance of over-broad repository access or unintended modification of files during execution.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.