ClawHub
Back to skill

Security audit

PDFlux SaaS Markdown

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed document-to-Markdown connector that uploads a user-selected file to PaodingAI/PDRouter for conversion.

Install only if you are comfortable sending the selected PDFs, Office files, or images to PaodingAI/PDRouter using your PAODINGAI_API_KEY. Avoid using it on confidential or regulated documents unless that external processing is approved for your use case.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill requires environment variables and performs outbound network access to an external API, but the skill file does not declare permissions in a clear, explicit way for policy enforcement or user review. This can weaken sandboxing and informed consent because users may not realize the skill can read secrets from the environment and transmit local document contents off-host.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill uploads a user-supplied local file to a third-party API, but the description and usage guidance do not prominently warn that document contents leave the local environment. This creates a data exfiltration and privacy risk, especially if users process sensitive PDFs, contracts, IDs, or internal documents without understanding they are being transmitted externally.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The default prompt says to "Always execute" the upload script for a local file, which is overly broad and can cause the agent to transmit user files without a narrowly scoped trigger or explicit user confirmation. In a document-processing skill, this is especially risky because users may ask analysis questions about local content without realizing the skill is instructed to immediately invoke an external conversion API.

Missing User Warnings

High
Confidence
97% confidence
Finding
The manifest instructs the agent to upload local PDFs, DOCX, PPT, and images to an external API using environment-based credentials, but it does not warn the user that local files will leave the local environment. This creates a significant data exfiltration and privacy risk, particularly because the supported inputs commonly contain sensitive business, legal, financial, or personal information.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/upload_to_markdown.js:8