Back to skill

Security audit

paper2slides

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to do what it claims: turn user-provided academic PDFs into slide decks, with no hidden persistence, exfiltration, or destructive behavior found.

Installers should understand that giving this skill a PDF URL will cause the agent to fetch that remote document, and generated slides should be reviewed for accuracy and language/template fit. Use trusted PDF sources and be cautious with optional PPTX generation if it proposes installing python-pptx.

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
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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The slide template hard-codes bilingual Chinese/English outline text and Chinese narrative phrases, which imposes a specific locale/language presentation style on all generated output. The file does not indicate that this is optional, user-selectable, or justified as a region-specific template.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly supports PDF URLs, which causes the agent to retrieve remote content over the network, but the description does not warn users about that behavior. This can lead to unexpected outbound requests, privacy leakage of user-supplied URLs or metadata, and exposure to untrusted remote documents without informed user consent.

Content

No source excerpt is available for this finding.