ClawHub
Back to skill

Security audit

Nano PDF工具（免费版）

Security checks across malware telemetry and agentic risk

Overview

This is a simple PDF helper skill whose file and command access matches its stated purpose, though users should be careful with edits and callback URLs.

Install only if you are comfortable letting the agent read and write PDFs in your workspace and run Python PDF tooling. When using it, specify exact input and output paths, avoid overwriting originals, and use callback URLs only for endpoints you trust.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Confidence
83% confidence
Finding
The example trigger phrase for reading a PDF is broad enough that ordinary user requests could unintentionally activate the skill. In an agent environment with read/exec/write tools, overbroad activation increases the chance of unintended file access or processing without clear user confirmation.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The generic creation trigger lacks constraints on what may be created and under what conditions, which can cause accidental invocation and unintended file generation. In this skill, the presence of write and exec capabilities makes vague creation commands more risky because they could lead to unreviewed filesystem changes.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill advertises page operations and editing but does not warn users that these actions can modify or destroy document contents. In a tool-enabled agent context, missing warnings and confirmation steps increase the risk of accidental destructive changes to user files.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The callback_url parameter introduces network-based data transmission, but the skill provides no privacy or security warning about sending results to external destinations. If used carelessly, this could expose document contents, metadata, or processing status to attacker-controlled endpoints, especially in an agent environment that may handle sensitive local files.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.