Security audit
Security checks across malware telemetry and agentic risk
This skill appears to be a real knowledge-search tool, but it exposes highly privileged database access and sensitive WhatsApp knowledge workflows that require careful review before installation.
Review this skill before installing it. It is not clearly malicious, but it is designed around sensitive private knowledge stores and privileged Supabase access. Only use it in an environment where the Supabase service-role key, WhatsApp conversation data, index files, and embedding endpoint are intentionally available to the agent, and avoid remote embedding APIs unless you are comfortable sending document text and queries there.
def get_embedding(text: str, model: str, api_url: str) -> list[float]:
"""Get embedding from Ollama API."""
response = requests.post(
f"{api_url}/api/embeddings",
json={"model": model, "prompt": text},
timeout=120def get_embedding(text: str, model: str, api_url: str) -> list[float]:
"""Get embedding from Ollama API."""
response = requests.post(
f"{api_url}/api/embeddings",
json={"model": model, "prompt": text},
timeout=60VirusTotal findings are pending for this skill version.
No suspicious patterns detected.