Security audit

Pdf Extract

Security checks for vulnerabilities and agentic risk

Overview

The skill is for PDF extraction and shows no exfiltration or destructive behavior, but it relies on executing an external helper path that the artifact does not install or prove.

Review this before installing because it assumes an existing ~/.openclaw/workspace/pdf-tools helper that is not shipped by the skill. Only use it when you trust that local helper and intentionally want the agent to extract content from the specified PDF; avoid broad extraction of confidential documents and avoid leaving sensitive extracted text in shared temporary files.

SkillSpector

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 activation guidance is very broad and encourages immediate use for nearly any PDF-related request, which can cause the skill to trigger on general document tasks without sufficient context or user confirmation. In practice, this increases the chance of processing sensitive local PDFs unnecessarily and can expand the skill’s access and use beyond the minimum needed for the task.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The skill explains how to extract and pipe PDF contents for downstream analysis but does not warn that extracted text may contain sensitive personal, financial, legal, or proprietary information. This omission can lead users or agents to expose document contents more broadly in logs, temp files, or subsequent model prompts than intended.

Static analysis

No suspicious patterns detected.