Back to skill

Security audit

Test Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill appears aimed at legitimate creative media generation, but it asks for broad local execution and file access while the referenced implementation files are missing from the package.

Review this carefully before installing. Use it only in a sandboxed project directory with non-sensitive inputs and provider API keys you are comfortable using for media generation. Avoid giving it access to private repositories, credentials, or broad home-directory files until the missing scripts/templates are included and command permissions are narrowed.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:7
Finding

Overly Broad Local Code Execution and Filesystem Permissions

Content
View full analysis
Remediation
View remediation
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
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill description is framed broadly enough that an agent could invoke it for many loosely related creative tasks without strong activation boundaries or explicit user confirmation. Because the skill can make network requests, generate third-party content, and write files, overbroad routing increases the chance of unintended execution and external data disclosure during ordinary prompts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation describes capabilities and provider routing but does not prominently warn that prompts, uploaded media, and possibly project content are transmitted to third-party APIs and that output files and task-tracking artifacts are written locally. This can cause users or higher-level agents to disclose sensitive content or modify the filesystem without informed consent.

Content

No source excerpt is available for this finding.