Security audit
Security checks across malware telemetry and agentic risk
This is a coherent video-generation skill, but users should understand that it writes local project files and can send scripts/topics to external research, asset, and TTS services.
Install only if you are comfortable with a coding agent writing video project files, running ffmpeg/npx/Remotion, and sending script or topic content to search, stock-asset, and TTS providers. Avoid confidential scripts unless you configure acceptable providers and review privacy terms; back up user_prefs.json before resetting preferences and keep dependencies updated.
},
}
resp = requests.post(endpoint, headers=headers, json=payload, timeout=timeout_sec)
resp.raise_for_status()
data = resp.json()},
}
resp = requests.post(url, headers=headers, json=payload, timeout=120)
resp.raise_for_status()
data = resp.json()success = False
for attempt in range(1, 4):
try:
url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice}/with-timestamps"
payload = {
"text": chunk,
"model_id": model,},
}
resp = requests.post(url, json=payload, headers=headers, timeout=120)
resp.raise_for_status()
data = resp.json()1. Assets the user explicitly supplied or requested → always plan them. 2. Free sources (user files, assetSeeker stock, Iconify icons) → plan and resolve without asking. 2–4 well-placed assets beat wall-to-wall media; text-only sections remain perfectly valid. 3. Paid generation (imagenCN / videogenCN) → register as `planned` / `pending_confirmation` with a `--cost-estimate`; present the cost sheet and
'--public-dir', output_dir,
]
print(f" Rendering: {' '.join(cmd)}")
result = subprocess.run(cmd, capture_output=True, text=True)
if result.returncode != 0:
print(f" Render failed: {result.stderr.strip()}", file=sys.stderr)
return Falsewith open(tmp_file, 'wb') as f:
f.write(resp.content)
result = subprocess.run(
["ffmpeg", "-y", "-i", tmp_file, "-ar", "48000", "-ac", "1", part_file],
capture_output=True, text=True)
if result.returncode != 0:raise RuntimeError(f"FFmpeg normalize failed: {result.stderr}")
os.remove(tmp_file)
probe = subprocess.run(
["ffprobe", "-v", "quiet", "-show_entries", "format=duration", "-of", "csv=p=0", part_file],
capture_output=True, text=True)
chunk_duration = float(probe.stdout.strip()) if probe.stdout.strip() else 064/64 vendors flagged this skill as clean.
No suspicious patterns detected.