Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward Baidu AI PPT generator, but users should know their prompt content is sent to Baidu.
Install only if you are comfortable using Baidu's AI PPT service and providing a BAIDU_API_KEY. Treat any PPT topic, outline material, or web_content as data that may be sent to Baidu, and avoid confidential business, personal, or regulated content unless your policy allows it.
The description omits operationally significant behavior including subprocess/script execution, dependence on a secret API key, and external theme-list/API access. Hidden execution and secret use are security-relevant because they expand the attack surface and can lead to unauthorized network actions or accidental exposure of sensitive configuration if the runtime grants broad shell/env access.
The description omits operationally significant behavior including subprocess/script execution, dependence on a secret API key, and external theme-list/API access. Hidden execution and secret use are security-relevant because they expand the attack surface and can lead to unauthorized network actions or accidental exposure of sensitive configuration if the runtime grants broad shell/env access.
The description omits operationally significant behavior including subprocess/script execution, dependence on a secret API key, and external theme-list/API access. Hidden execution and secret use are security-relevant because they expand the attack surface and can lead to unauthorized network actions or accidental exposure of sensitive configuration if the runtime grants broad shell/env access.
The skill advertises executable capabilities via required binaries and environment variables and clearly instructs running Python scripts that call an external API, but it does not declare an explicit tool scope such as allowed tools or permissions. That creates a governance gap: an agent may grant broader shell, network, or env access than users expect, increasing the chance of unintended command execution or data egress.
The skill asks users for PPT topics and sends them to Baidu AI, but the description does not warn users that their input is transmitted to a third-party service. This is dangerous because topics may contain proprietary plans, internal reports, or personal data, leading to unintended disclosure and possible compliance violations.
The function sends the user-provided query to Baidu's external generate_outline API, which is a real data egress path. In an agent/skill context, prompts may contain sensitive user or enterprise data, and the code performs no consent check, redaction, or data-classification guard before transmitting it to a third-party service.
outline = ""
chat_id = ""
query_id = ""
with requests.post(URL_PREFIX + "generate_outline", headers=headers, json=params, stream=True) as response:
for line in response.iter_lines():
line = line.decode('utf-8')
if line and line.startswith("data:"):
This request sends not only the query and generated outline/title, but also optional web_content to Baidu's external generate_ppt_by_outline endpoint. Because web_content may include large bodies of copied page text or sensitive internal material, this creates a broader exfiltration risk than the outline step, especially in enterprise agent deployments.
"web_content": web_content,
"enable_save_bos": True,
}
with requests.post(URL_PREFIX + "generate_ppt_by_outline", headers=headers, json=params, stream=True) as response:
if response.status_code != 200:
print(f"request failed, status code is {response.status_code}, error message is {response.text}")
return []
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
]
start_time = int(time.time())
process = subprocess.Popen(
cmd,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
No suspicious patterns detected.