Back to skill

Security audit

Video Stitcher

Security checks for vulnerabilities and agentic risk

Overview

This skill gives normal video-stitching instructions using FFmpeg or Remotion, with no hidden persistence or unrelated data access found.

Install only if you are comfortable giving the agent access to the video, subtitle, and music paths or media URLs you provide. Use trusted media sources and review generated FFmpeg commands before running them on sensitive files.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language instructions and documentation are presented entirely in Chinese, aside from a few embedded English trigger phrases, and there is no indication that users can choose another language. Per the policy, forcing a specific language without user opt-in is a locale-policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly allows clip inputs as local paths or URLs, but it does not warn that processing those values may cause the system to fetch remote content or access internal files. In a video-processing context, this can enable SSRF-like network access, unintended retrieval of attacker-controlled media, or processing of sensitive local/remote resources without user awareness.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.