ClawHub
Back to skill

Security audit

Donson Intelligent Editing

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward FFmpeg command guide, with the main caution that users should check output filenames before running generated media commands.

Before installing, understand that this skill helps an agent produce FFmpeg shell commands. Review generated commands before running them, especially output paths, large batch jobs, and any overwrite flags such as -y. It does not request credentials, install software, run background processes, or add persistence.

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
Confidence
96% confidence
Finding
The trigger list includes several broad, generic terms such as "ffmpeg," "codec," "mp4," and "mkv," which can cause the skill to activate in contexts that do not actually require this specialized capability. Over-invocation increases the chance that the agent emits shell commands unnecessarily, which is risky because this skill is scoped to implementation and outputs executable commands.

Missing User Warnings

Low
Confidence
83% confidence
Finding
The examples provide direct FFmpeg write operations but do not warn about overwrite behavior, output-path safety, or the risk of replacing important media files during iterative use. In a skill that emits shell commands, omission of such safeguards can lead to accidental data loss, especially when users adapt examples by reusing input/output names or adding overwrite flags.

Static analysis

No suspicious patterns detected.