Back to skill

Security audit

scroll-animation-workflow

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with high confidence: they report no AIG findings, while Skillspector flags privacy warnings missing from instructions to share assets and prompts with third-party services.

Before installing, consider whether you are comfortable sharing the assets and prompts you use with third-party services. Avoid sending confidential or personal information unless you have permission and have reviewed those services’ privacy and retention terms.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

The workflow instructs users to upload website assets to third-party services without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

Steps 2–4 instruct users to upload frames to Flow, provide the video to EZGIF, and give images and prompts to an AI coding tool. Although these transfers are performed by the user, the workflow never warns that the assets and prompts leave their control or advises against including confidential business content or personal data.

Content

No source excerpt is available for this finding.

The workflow instructs users to upload website assets to third-party services without a privacy warning.

Low
Category
Output Handling
Confidence
87% confidence
Finding

The workflow directs users to upload their frames to Flow and process the resulting video with EZGIF, rather than merely listing available tools. It does not warn that these steps share assets with external services, which matters if frames contain confidential designs, customer information, or other sensitive content.

Content

No source excerpt is available for this finding.