Security audit

Website ScreenshotOne (by ScreenshotOne)

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent ScreenshotOne helper, but it should be reviewed because it can send private pages, cookies, headers, and authorization data to an external screenshot service without clear warnings or confirmation guardrails.

Install only if you are comfortable routing screenshot targets through ScreenshotOne. Do not use it for private, internal, regulated, or authenticated pages unless you have approval, and avoid sending production cookies, bearer tokens, API keys, or sensitive headers.

SkillSpector

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 (4)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill instructs users to send target URLs to a third-party screenshot service but does not warn that page contents, query strings, and any rendered data will be transmitted off-platform. In this context, the omission matters because users may apply the skill to internal, sensitive, or user-specific pages without realizing they are disclosing data to an external processor.

Missing User Warnings

High

Confidence: 98% confidence
Finding: The skill suggests using cookies, headers, and authorization as request context without warning that these values may contain live session tokens, API keys, or bearer credentials that would be transmitted to the external API. This is especially dangerous in a screenshoting skill because it can enable capture of authenticated pages while simultaneously exposing credentials to a third party.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The skill enables implicit invocation without any visible trigger constraints, allowing the agent to call an external screenshot-taking capability automatically based on vague user intent. Because this skill can fetch arbitrary URLs and save results locally, unintended invocation could cause unreviewed outbound requests, capture internal or sensitive web resources, or perform actions the user did not explicitly approve.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The reference explicitly instructs users to supply sensitive inputs such as `access_key`, `authorization`, `cookies`, custom headers, and storage settings for a third-party screenshot service, but it provides no warning about secret handling, scope minimization, or the risk of transmitting session/auth data off-platform. In an agent skill context, this omission can lead users or downstream agents to pass live credentials, authenticated cookies, or internal URLs to an external API, creating avoidable exposure of secrets and private content.

Static analysis

No suspicious patterns detected.