Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it claims: it uses Baidu's PPT API to generate presentations from user-provided topics, with no hidden persistence or unrelated local data access found.
Install only if you are comfortable sending your PPT topic and any optional web content to Baidu's API using your BAIDU_API_KEY. Avoid submitting secrets, private business plans, regulated data, or other sensitive content unless your Baidu account and policies allow that use.
The skill markets template selection as smart/content-driven, but the documented fallback to random selection and use of external API/theme retrieval without declared permissions undermines transparency. This can mislead users about how their content is processed and what remote services are involved, increasing privacy and trust risks.
The skill markets template selection as smart/content-driven, but the documented fallback to random selection and use of external API/theme retrieval without declared permissions undermines transparency. This can mislead users about how their content is processed and what remote services are involved, increasing privacy and trust risks.
The skill markets template selection as smart/content-driven, but the documented fallback to random selection and use of external API/theme retrieval without declared permissions undermines transparency. This can mislead users about how their content is processed and what remote services are involved, increasing privacy and trust risks.
The skill declares code execution prerequisites and an API key, and its workflow instructs the agent to run Python scripts that necessarily use shell, environment variables, and network access, but it does not declare any explicit tool scope or permissions. This weakens least-privilege controls and can lead to broader-than-expected execution capability for a skill that sends user data to an external service.
The workflow asks for a user-provided PPT topic and sends it to Baidu AI services, but the skill description does not warn users that their prompt/content will leave the local environment. This is a privacy and consent issue, especially if users include sensitive business, educational, or personal material in the topic or slide request.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
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 code sends the user's query to a remote Baidu service in generate_outline, and later sends the query, generated outline, title, and optional web_content to another remote endpoint. While the script prints template-selection status and missing-key errors, it does not clearly disclose to the user that their provided content will be transmitted to an external service.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
"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 []
This code uses Chinese-only category names and later exposes them in command-line help and status output, which imposes a specific language/locale on users. The file does not provide any opt-in, alternate locale, or documented justification for restricting interaction to Chinese.
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,
The argument help text and auto-suggested category output are presented only in Chinese, which is a natural-language policy concern when no language choice is offered. Users who do not read Chinese cannot meaningfully understand or control the skill's behavior.
The skill presents template categories and output examples in Chinese and appears oriented around Chinese-language styles, but it does not state that the skill is China/Chinese-specific or give users a language/locale choice. This can amount to an implicit locale constraint without opt-in or justification.
The code accesses BAIDU_API_KEY from the environment and uses it as a bearer token in HTTP requests. Although this is functionally necessary, there is no comment, docstring, or user-facing notice explaining that the script depends on and transmits this credential to an external service.
No suspicious patterns detected.