Back to skill

Security audit

ecommerce-video-edit

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this video-editing skill suspicious because its remote-processing fallback may share footage with a third party without clearly warning users, and its install instructions use unpinned packages; no clear malicious intent was reported.

Before installing, consider whether you are comfortable with a hosted option that may share footage or media URLs with Varg; use it only after understanding and agreeing to that sharing. The installation commands also use unpinned packages. Skillspector inspected all four listed components, but marked its analysis partial because several references did not resolve, so the evidence is incomplete.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

The Varg fallback lacks a warning that user footage may be processed by a third-party service.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The description emphasizes local operation but offers a remote fallback without explicitly explaining that a third party would receive or access the footage. An agent following that fallback could expose unpublished product material or identifiable creator footage without informed permission.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The command invokes an unpinned npm package through npx, potentially downloading and executing a changing release with the user's privileges. Although this is an installer rather than an MCP server, the underlying supply-chain exposure is real; there is no evidence the command itself is malicious.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx ffmpeg-static'.

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The suggested npx invocation can download an unpinned ffmpeg-static package and run package installation code with the agent's privileges. This is not an MCP server reference, but it still introduces avoidable supply-chain risk into an otherwise local media-editing workflow.

Content

No source excerpt is available for this finding.

The remote-processing fallback lacks a warning that user footage will be accessed by a third-party service.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The fallback instructs the agent to submit commands and media URLs to a hosted service without requiring permission to disclose the footage. Naming the service and mentioning credit estimates does not establish informed consent for third-party access, particularly for private or unreleased footage.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 158)May include surrounding context.

md
## No shell? Run it on varg

Send the same command to the varg `ffmpeg` tool (MCP `call_tool`, or `POST https://api.varg.ai/v2/ffmpeg`). Inputs and outputs are URLs. It is priced in credits, with an estimate before anything runs.

## Related skills