Security audit
Security checks for vulnerabilities and agentic risk
This skill fetches a public PizzINT webpage and formats a report, with no evidence of credential access, persistence, local data collection, or destructive behavior.
Before installing, understand that the skill is mostly Chinese-language and may trigger on broad geopolitical terms. It contacts pizzint.watch or asks the agent to open that site in a browser to gather public OSINT-style data; treat the resulting threat report as informal correlation, not as authoritative intelligence or a basis for financial or operational decisions.
The skill documentation is primarily written in Chinese, including the description, setup context, and risk guidance, while embedding some English terms. This imposes a specific language on users without stating that the skill is Chinese-only, offering an alternative language, or requesting user opt-in, which matches the locale/language policy concern.
The natural-language instructions and usage guidance are presented exclusively in Chinese, but the document does not state that the skill is region-specific or offer an opt-in language choice. Under the stated policy, forcing a specific language without user opt-in is a locale-policy violation.
The trigger list includes broad terms such as '军事情报' and '地缘紧张' that can match many unrelated requests, causing the skill to activate outside its intended PizzINT-specific scope. Over-broad invocation increases the chance of inappropriate use in sensitive geopolitical contexts and can route generic intelligence queries into a specialized, potentially misleading workflow.
This Python file contains natural-language instructions and descriptions primarily in Chinese, including the module header and many user-facing messages. Under the policy rule for language/locale, forcing a specific language without user opt-in is a violation unless the locale restriction is explicitly documented and justified, which is not present here.
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
def get_pizzint_data():
"""从 pizzint.watch 获取数据"""
try:
result = subprocess.run(
['curl', '-s', '--max-time', '10', 'https://pizzint.watch/'],
capture_output=True, text=True, timeout=15
)