ClawHub
Back to skill

Security audit

media-composition

Security checks for vulnerabilities and agentic risk

Overview

This skill provides straightforward FFmpeg media-composition instructions, with only minor caution around broad activation words and trusting manifest-defined media paths.

Install this if you want Codex to compose local media with FFmpeg. Review manifests before use, especially any listed paths or prerequisite commands, and invoke it for explicit media-composition tasks rather than generic tutorial or media requests.

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 (1)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger list includes very generic terms such as 'media', 'combine', 'stitch', and 'tutorial', which can cause this skill to activate for requests well outside narrowly scoped FFmpeg composition tasks. Over-broad activation increases the chance an agent will inappropriately select this skill and execute shell-oriented media-processing guidance on unrelated user input, expanding attack surface and enabling prompt/skill misrouting.

Static analysis

No suspicious patterns detected.