ClawHub
Back to skill

Security audit

sanxin_form_filler1

Security checks across malware telemetry and agentic risk

Overview

This skill is a local Word form-filling helper that can edit and save documents, but its behavior matches its stated purpose and shows no hidden data sharing or unsafe persistence.

Install only if you are comfortable with local Word automation through pywin32. Use copies of blank forms, choose a distinct output path, and manually review the generated document before relying on it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger wording is broad enough to match ordinary document-help requests, which can cause the skill to activate in situations where the user did not clearly consent to automated document modification. In this skill’s context, activation leads toward editing and saving Word files, so ambiguous invocation increases the risk of unintended file changes or processing of sensitive local documents.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation describes form-filling behavior but does not clearly warn users that the skill will modify and save Word documents automatically. In a tool that accesses local files via Word automation, missing disclosure weakens informed consent and can lead to accidental overwrites, unintended persistence of sensitive content, or silent creation of altered documents.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.