Beamer Pipeline Public

Security checks across malware telemetry and agentic risk

Overview

This is a coherent local Beamer-slide pipeline, with the main caution that it can download image URLs from input Markdown and run configured local agent or LaTeX commands.

Install only if you are comfortable with a local slide-generation pipeline that writes an output workspace, may call your configured OpenClaw agents or LaTeX tools, and downloads Markdown image URLs by default. Use --skip-assets for untrusted documents or when outbound network requests are not acceptable, and use --no-agent or a reviewed --agent-cmd if you do not want the skill invoking local agents.

SkillSpector

By NVIDIA
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 (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script automatically fetches attacker-controlled remote URLs extracted from Markdown and writes the retrieved content to local disk without any consent, warning, or allowlist. This creates a real SSRF-style/network reach-out and untrusted file ingestion risk in build or agent environments, potentially exposing internal services, leaking network metadata, or storing unexpected content locally.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal