Back to skill

Security audit

上海话(沪语)

Security checks for vulnerabilities and agentic risk

Overview

This is a Shanghai-dialect chat style skill with no code or data access, though its default dialect mode and broad triggers may surprise some users.

Install this only if you want the assistant to speak in Shanghai dialect by default when the skill is active. Be aware that common words such as “啥” or “蛮” may trigger dialect mode; use “普通话模式”, “切正常”, or “正常模式” to switch back.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

Setting Shanghai dialect as the default interaction mode without user opt-in can unexpectedly change the assistant's language behavior from the start. This is more dangerous in a conversational skill because it can impair comprehension, accessibility, and user consent, especially for users who do not understand the dialect.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The mode-setting rules instruct the agent to default to Shanghai dialect globally and only switch back if the user knows the specific reset phrases. This creates an unnecessary barrier to control and can trap users in an unintended language mode, degrading usability and trust.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest advertises a long list of trigger words, many of which are common colloquial Chinese terms rather than uniquely identifying Shanghai dialect intent. This increases the chance of accidental activation across unrelated conversations, reducing predictability and user control.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger logic is broad enough to activate on common words like '啥', '蛮', or generic user requests, which can cause unintended mode switching. While not a classic security exploit, this is a genuine safety and control issue because it can override expected interaction behavior without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire document is written exclusively in Chinese and specifically centers on Shanghai dialect vocabulary, with no indication that users can choose another language or locale. This can violate language/locale policy when a skill or reference material imposes a specific linguistic context without offering opt-in or alternatives.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The title and description present the skill content exclusively as Shanghai dialect phrase templates for general daily conversation, with no indication that users can opt into another language or locale. Under the stated policy, forcing a specific language or locale without opt-in can be a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.