ClawHub
Back to skill

Security audit

inSaiAI Intelligent Editing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward FFmpeg command guide; it can generate file-writing media commands, but that behavior is disclosed and fits its purpose.

Install this if you want FFmpeg command help. Review generated commands before running them, use distinct output filenames, and be careful with batch conversion or streaming commands because they can create files or send media to a configured endpoint.

A.I.G

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

SkillSpector

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad terms such as "ffmpeg," "codec," "mp4," and "mkv," which can cause the skill to activate in situations that do not actually require this specialist behavior. Overbroad activation increases the chance that shell-command-oriented guidance is injected into unrelated workflows, expanding the attack surface and creating opportunities for unintended command generation or unsafe file operations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The documentation repeatedly provides commands that create or overwrite output files but does not warn users about filesystem side effects, naming collisions, or destructive behavior when reusing paths. In a shell-command-output skill, this matters because generated commands may be run directly, making accidental data loss or overwriting of existing media files more likely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.