ClawHub
Back to skill

Security audit

Pdf Figure Extractor

Security checks for vulnerabilities and agentic risk

Overview

This skill provides straightforward instructions for extracting figures from academic PDFs and does not show hidden, persistent, or unrelated behavior.

Install this if you want an agent to process local academic PDFs to locate captions and crop figures. Review extracted images before using them, and be aware that the skill assumes PDF files are intentionally provided for this workflow.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger keywords are generic enough to activate on broad PDF/image-related requests without clear scope limits, confirmation requirements, or exclusion conditions. That increases the chance the skill is invoked in unintended contexts, causing the agent to perform document-processing actions when the user did not explicitly request this specialized workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill metadata and all user-facing instructions are written entirely in Chinese, with no indication that the user may choose another language or that the locale is intentionally restricted. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.