Security audit

Universal Doc Processor

Security checks for vulnerabilities and agentic risk

Overview

This document-processing skill reads and temporarily retains uploaded files for multi-turn work, which fits its stated purpose and shows no exfiltration or destructive behavior.

Install only if you are comfortable with uploaded documents being parsed when received and retained for the session, potentially until the stated 72-hour inactivity cleanup. Avoid highly sensitive documents unless the host environment controls upload paths and provides an acceptable deletion or reset process.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill states that uploaded files are stored and retained across turns, and later notes a 72-hour timeout, but it does not prominently warn users up front about retention, session persistence, or data handling. This creates a privacy risk because users may upload sensitive documents assuming one-time processing, while the skill keeps them available for later reuse.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The skill immediately parses uploaded files and stores extracted content in memory without any user-facing notice, minimization control, or consent boundary. In a document-processing context this can expose sensitive document contents to downstream task handling, logs, or future reuse across turns, especially because files and parsed content persist in object state for multi-round interactions.

Static analysis

No suspicious patterns detected.