Back to skill

Security audit

short-form-ffmpeg-cookbook

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because scanners found unpinned package commands and a remote media-processing option without a privacy warning; no clear malicious intent was reported.

Before installing, consider whether you are comfortable with unpinned package downloads and a remote processing option that may share media or URLs with a third party. The scan covered both reported Markdown files but was marked partial because some local references could not be resolved, 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 (4)

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

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The command invokes an unpinned npm package through npx, potentially downloading and executing a changing release with the user's privileges. This is a supply-chain exposure rather than an unversioned MCP server reference; the installation context explains the command but does not eliminate the risk.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
85% confidence
Finding

The fallback recommends fetching an unpinned npm package through npx, introducing mutable third-party code into an otherwise local media-processing workflow. Although ffmpeg-static is not an MCP server and may not provide a directly runnable CLI, package fetching and installation can still introduce supply-chain risk.

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 90)May include surrounding context.

md
## No shell

Send the same command to the varg `ffmpeg` tool (MCP `call_tool`, or `POST https://api.varg.ai/v2/ffmpeg`), or use its `resize`, `trim` and `slice` tools, with URLs in and out. Priced in credits, with an estimate before it runs. Tutorials: https://skills.varg.ai/burn-captions-with-ffmpeg/, https://skills.varg.ai/crop-a-video-to-vertical-with-ffmpeg/, https://skills.varg.ai/trim-and-join-video-clips-with-ffmpeg/, https://skills.varg.ai/add-music-to-a-video-with-ffmpeg/.

The no-shell workflow sends user media to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The no-shell fallback directs the agent to process media through a third-party API without requiring explicit consent to disclose that media. Although the service and credit costs are identified, users attracted by the local-processing description may not realize that this route exposes footage, audio, subtitles, or access-bearing media URLs to another provider.

Content

No source excerpt is available for this finding.