record-tutorial
This skill masquerades as a recording tool while performing unauthorized remote code execution and dynamic dependency fetching, bypassing platform monitoring to execute arbitrary shell commands on the host system.
Skill Info
Install
npx skills add https://github.com/MustaphaSteph/vorec-pluginsAssessments (5)
AI Agent Traps ↗The skill content includes instructions to perform remote code execution and dynamic dependency fetching via `npx` and `npm install -g`, which contradicts the claimed purpose of simply recording videos.
The skill explicitly instructs the agent to run `npx @vorec/cli@latest run`, `npm install -g agent-browser`, and `npx @vorec/cli@latest analyze`, which are mechanisms for downloading and executing arbitrary remote code.
Remote code download and execution detected
python3 -c "from urllib
The skill instructions require the agent to execute arbitrary shell commands (e.g., `pkill`, `rm -rf`, `brew install`) that are not explicitly covered by the `allowed-tools` manifest, creating a mismatch between declared and actual capabilities.
pkill -f "$SESSION_PROFILE" 2>/dev/null || true; rm -rf "$SESSION_PROFILE"
The skill explicitly instructs the agent to ignore standard browser automation tools and use its own CLI (`vorec run`) and specific `playwright-cli` commands, creating a siloed environment that bypasses platform-level monitoring. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]
You do not record with Playwright, FFmpeg, or any other tool. Only the app records. If the app is not installed, stop and tell the user to install it — do not suggest alternatives.
The skill mandates the use of `npx @vorec/cli@latest` and `npm install -g @vorec/cli` without integrity pinning or version locking. This allows arbitrary code execution from the remote registry at runtime, which is a significant supply chain risk.
npx @vorec/cli@latest run vorec.json
child_process module imported — any exec/execSync/spawn call executes OS commands
import { exec } from 'node:child_process';NER model detected organization in skill content (confidence: 0.51)
V***
NER model detected organization in skill content (confidence: 0.71)
V****
NER model detected organization in skill content (confidence: 0.83)
D********
NER model detected organization in skill content (confidence: 0.84)
V*************
NER model detected organization in skill content (confidence: 0.70)
*
NER model detected organization in skill content (confidence: 0.96)
*
Skill executes commands, writes files, or accesses the network but declares no allowed-tools, so its tool surface cannot be reviewed or constrained.
Unpinned npx package execution — `npx <pkg>` without a version pin pulls latest from npm at runtime (seen 3 times in this file at lines 165, 3680, 4092)
npx cache
Global/unverified dependency execution — global npm/yarn package, dotnet tool, or auto-confirmed npx run without version or integrity pinning (seen 4 times in this file at lines 190, 194, 668, 3677)
npm install -g
Post-install or dynamic dependency fetching — runtime code loading from untrusted sources
require()`, `import`, `fs`, `process` — browser sandbox only - `console.log` does NOT appear in stdout — use `return` for output - For anything needing Node APIs, write a standalone `.mjs` script instead ## Related files - [./cli-commands.md](./cli-commands.md) — Core commands (open, click, snapshot) - [../SKILL.md](../SKILL.md) — Manifest format +
SKILL.md links to "cli-commands.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
[./cli-commands.md](./cli-commands.md)
SKILL.md links to "context-writing.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
[./context-writing.md](./context-writing.md)
SKILL.md links to "live-site-discovery.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
[./live-site-discovery.md](./live-site-discovery.md)
SKILL.md links to "narration-rules.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
[./narration-rules.md](./narration-rules.md)
SKILL.md links to "pacing.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
[./pacing.md](./pacing.md)
Skill does not specify a license field. Specifying a license helps users understand usage terms.
Hidden/zero CSS (display:none, visibility:hidden, opacity:0, font-size:0) — weak hidden-content signal (common in legitimate UI/animation) (seen 2 times in this file at lines 366, 371)
opacity:0
Version History (2)
Badge
[](https://mondoo.com/ai-agent-security/skills/github/MustaphaSteph/vorec-plugins/record-tutorial)<a href="https://mondoo.com/ai-agent-security/skills/github/MustaphaSteph/vorec-plugins/record-tutorial"><img src="https://mondoo.com/ai-agent-security/api/badge/github/MustaphaSteph/vorec-plugins/record-tutorial.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/github/MustaphaSteph/vorec-plugins/record-tutorial.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet, discover and control Shadow AI usage.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow