Security checks across malware telemetry and agentic risk
The skill performs legitimate audio transcription, but its optional LLM features can send sensitive transcripts to Claude or GitHub Copilot while the documentation also claims local-only privacy.
Install only if you are comfortable with dependency installation and with transcript text potentially being processed by Claude or GitHub Copilot under your existing accounts. For confidential, regulated, or client recordings, use transcript-only/local Whisper mode or review and modify the scripts so external LLM calls and runtime pip installs cannot run automatically.
except ImportError:
RICH_AVAILABLE = False
print("⚠️ Installing rich for better UI...")
subprocess.run([sys.executable, "-m", "pip", "install", "--user", "rich"], check=False)
from rich.console import Console
from rich.prompt import Prompt
from rich.panel import Panelfrom tqdm import tqdm
except ImportError:
print("⚠️ Installing tqdm for progress bars...")
subprocess.run([sys.executable, "-m", "pip", "install", "--user", "tqdm"], check=False)
from tqdm import tqdm
# Whisper engines# Tentar via gh copilot
console.print("[dim] Invocando prompt-engineer...[/dim]")
result = subprocess.run(
['gh', 'copilot', 'suggest', '-t', 'shell', raw_prompt],
capture_output=True,
text=True,progress.add_task(description=f"🤖 Processando com {cli_tool}...", total=None)
if cli_tool == 'claude':
result = subprocess.run(
['claude', '-'],
input=full_prompt,
capture_output=True,timeout=timeout
)
elif cli_tool == 'gh-copilot':
result = subprocess.run(
['gh', 'copilot', 'suggest', '-t', 'shell', full_prompt],
capture_output=True,
text=True,VirusTotal findings are pending for this skill version.