ClawHub
Back to skill

Security audit

A3报告技能

Security checks across malware telemetry and agentic risk

Overview

This skill coherently helps create an editable A3 report and its local file/image handling is disclosed and proportionate to that purpose.

Before installing, understand that this skill creates a local editable HTML report and the generated file can embed images you add in the browser. Keep the output path to a normal project/output folder and avoid putting sensitive information into reports you plan to share.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
78% confidence
Finding
The skill invokes a local script to generate an HTML file and explicitly writes output to `./output/a3_report.html`, so it does exercise file-write capability despite declaring no permissions. Undeclared file access weakens review and consent boundaries: a user or platform may assume the skill is documentation-only, while it can read templates and write generated artifacts on disk.

Tp4

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding
The documented behavior promises structured interactive questioning and validation, but the detected implementation behavior includes local image handling, browser-side save/export, and editable HTML features not reflected in the description. This mismatch is dangerous because reviewers and users may approve the skill for one workflow while it actually processes local files and produces active HTML content with broader data-handling surface area.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.