Security audit

Rendshot

Security checks across malware telemetry and agentic risk

Overview

Rendshot is a coherent image rendering and screenshot helper, but users should treat it as a third-party service that may receive prompts, HTML, template data, URLs, and an API key.

Install only if you are comfortable sharing render inputs, prompts, template variables, screenshot target URLs, and a Rendshot API key with Rendshot or your configured self-hosted endpoint. Avoid sensitive HTML, secrets, authenticated pages, localhost/internal URLs, cloud metadata endpoints, and regulated data unless you have explicit authorization and controls in place.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger phrases are broad enough to match common requests like 'generate thumbnail' or 'screenshot this page,' which can cause the skill to activate unexpectedly. In a skill that can fetch external URLs and render arbitrary HTML, over-broad invocation increases the chance of unintended network access, privacy issues, or misuse without clear user intent.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill describes screenshot and rendering capabilities but does not warn that using them may fetch third-party URLs or process untrusted HTML/CSS. This can lead users or upstream agents to submit sensitive internal URLs, authenticated pages, or attacker-controlled content without understanding the privacy and security implications.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal