Interactive Prototypes — Human + AI
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is primarily a link-returning portfolio skill, with optional developer-only screenshot/video helper scripts that should be run only deliberately.
Installing the skill should mainly enable an agent to return the public demo landing link. Treat the optional screenshot/video scripts as developer utilities: only run them if you want those outputs, and review any dependencies or referenced repository scripts first.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If you choose to run the optional publishing helpers, your environment will install third-party tooling and execute local scripts.
The optional screenshot workflow asks a user to install Python packages and a Playwright browser before running helper code. This is disclosed and purpose-aligned, but it depends on external package sources.
pip install -r requirements-screenshots.txt playwright install chromium python3 capture_screenshots.py
Run these optional commands only in a development environment you trust, and review the requirements and scripts before execution.
Running the helper will make network requests to the listed GitHub Pages demos and create local screenshot files.
The helper script launches browser automation, visits public demo pages, and writes screenshots. This is expected for the optional screenshot feature and is not part of the skill’s normal link-returning behavior.
BASE = "https://vziatkov.github.io/neuro" await page.goto(url, wait_until="networkidle", timeout=15000) await page.screenshot(path=path, type="png")
Use the helper only when you intentionally want to generate screenshots; otherwise the installed skill does not need it.
If you follow the optional video workflow, you may execute code outside the reviewed skill files.
The optional video-generation instructions reference a repository script that is not included in the provided skill manifest. This is not runtime behavior, but a user following the docs would need to inspect that external helper separately.
python3 SMM/process_video.py gemini_skill_demo.mp4 -o skill_demo_processed.mp4
Before running referenced repository scripts that are not included here, inspect the exact file from the repository and confirm it is trusted.