Security audit
Security checks across malware telemetry and agentic risk
This skill is a user-run Obsidian import tool that uses external vision-model APIs as advertised, but users should treat document uploads and generated vault writes as privacy-sensitive.
Install only if you are comfortable sending the selected documents' extracted pages or images to MiniMax, OpenAI, or Anthropic using your API key. Use a narrow source directory, avoid confidential or regulated files unless external provider use is approved, use simple category names without slashes or traversal, and review generated Markdown before relying on it.
# 清理临时目录
if os.path.exists(temp_dir):
subprocess.run(["rm", "-rf", temp_dir], capture_output=True)
print(f" -> 已保存: {output_md}")
return len(images)"max_tokens": 1000
}
resp = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload, timeout=60)
data = resp.json()
if "choices" in data and data["choices"]:]}]
}
resp = requests.post("https://api.anthropic.com/v1/messages", headers=headers, json=payload, timeout=60)
data = resp.json()
if "content" in data:65/65 vendors flagged this skill as clean.
No suspicious patterns detected.