Back to skill

Security audit

AppScreenshotStudio

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed screenshot-generation integration that reads app metadata and sends a limited project summary to its API, with no evidence of hidden persistence or destructive behavior.

Install this only for projects where you are comfortable sending selected app metadata, feature summaries, screen names, colors, and marketing copy to appscreenshotstudio.com. Review what the agent found before generation, avoid including secrets or private roadmap details, and keep the API key in an environment variable or secret manager.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The phrase "or wants to ship a new app" is ambiguous and much broader than screenshot generation, so it could match many ordinary release-related requests that are not actually asking for this skill. The trigger list does not provide exclusion conditions or clarify when release-related requests should not invoke the skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly instructs the agent to read multiple local project files and assemble codebase-derived context, then send that context to a third-party API. Without a prominent user-facing warning and explicit consent gate, sensitive business information, metadata, unreleased features, or internal copy can be exfiltrated outside the local environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

  • package.json / pubspec.yaml / Cargo.toml / build.gradle — app name, tech stack
  • Brand colors: tailwind.config.* (theme.extend.colors), SwiftUI Color(, Flutter ThemeData
  • Key screens: Next.js app/ routes, SwiftUI NavigationView/TabView, Flutter GoRouter
  • App Store metadata: Info.plist, fastlane metadata/, AndroidManifest.xml

Build this context:

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
98% confidence
Finding

This is a direct external transmission path that sends assembled codebase context to a remote service using a bearer-authenticated API call. Because the prior steps encourage harvesting information from README, manifests, routes, themes, and metadata, the outbound request can leak proprietary product plans or sensitive internal details if performed without strict scoping and consent.

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

3a. Create a project:

bash
curl -s -X POST https://appscreenshotstudio.com/api/v1/projects \
  -H "Authorization: Bearer $APPSCREENSHOTSTUDIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill requires an API key but does not warn users about safe credential handling, storage, rotation, or avoiding exposure in logs and shell history. In agent and terminal workflows, poor guidance around secrets can lead to accidental leakage or misuse of the bearer token.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.