Security audit
Security checks for vulnerabilities and agentic risk
This skill appears to do what it says: check SJTU Minhang laundry machine status through a Haier IoT API, without persistence, credential use, or unrelated data access.
Install this if you want SJTU Minhang laundry status lookups and are comfortable with the skill contacting Haier's IoT service when invoked. Be aware that its English trigger words are broad, so users should invoke it in clearly campus-laundry contexts, and maintainers should consider narrowing the triggers or documenting the network endpoint more explicitly.
The skill instructs the agent to run a Python script that performs network access, but the manifest does not declare any tool scope or permissions. This creates a capability transparency and policy-enforcement gap: the host may invoke networked behavior without explicit review, and users or operators cannot easily assess what external access the skill requires.
The trigger list contains broad everyday English terms like 'washer', 'dryer', and 'laundry', which can cause the skill to activate for loosely related conversations. Over-broad invocation can route user requests into a networked skill unexpectedly, increasing privacy risk, confusion, and the chance of unintended external calls.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
"pageSize": 100,
}
try:
resp = requests.post(API_URL, json=body, timeout=10)
resp.raise_for_status()
except requests.Timeout:
print("错误：请求超时，请检查网络连接", file=sys.stderr)
The skill defaults to Chinese building names and a specific campus location, which effectively constrains interaction to a particular locale and language context. While this may be intended, the file does not explicitly state that the skill is region-specific or offer a language/locale choice, which can conflict with organizational expectations around user language or locale opt-in.
This code presents its CLI description, help text, status labels, and error messages entirely in Chinese, which constitutes a language/locale constraint in natural-language content. There is no user opt-in or documented justification for forcing this locale, so it matches the policy-violation category for language choice.
No suspicious patterns detected.