Back to skill

Security audit

Yijuhua Chufangan

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese proposal-writing helper with broad activation language but no hidden data access, network behavior, persistence, or privileged actions.

Install this if you want Chinese-language proposal drafts and are comfortable with broad triggers like 'write a plan' producing a full structured document. Review any generated government, sensor, data-sharing, budget, or KPI claims before using them in real work.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (10)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrases are extremely broad, including common requests like '写方案', '帮我出个', and '给我一个方案', which can match many ordinary conversations unrelated to this skill. That creates a prompt-squatting risk where the skill may activate unexpectedly, override user intent, and steer the agent into producing structured outputs when the user did not actually request this specific capability.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger section includes vague phrases like '这个事怎么做' plus a catch-all condition covering nearly any described need scenario. In an agent ecosystem, this broad matching materially raises the risk of unintentional routing and prompt squatting, where this skill captures traffic meant for general assistance or other more appropriate skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description and examples are entirely framed in Chinese, including the core promise that the user only needs to 'say one sentence' to get a complete proposal. There is no indication that other languages are supported, no user opt-in for Chinese-only behavior, and no documented region-specific justification, which creates a language/locale policy concern.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The direct-output mode allows execution when the request is only loosely specified, such as general direction-setting or keyword presence, without a robust confirmation step. This increases the chance of accidental invocation and can cause the agent to generate authoritative-looking documents from ambiguous input, potentially displacing safer clarification behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file describes connecting utility, traffic, and public-opinion data and deploying IoT sensors for real-time monitoring, which can affect privacy and system integrity. Under the markdown criteria for SQP-2, the description should include a clear warning or disclosure about data governance, privacy impact, or monitoring implications, but none is present in this section or elsewhere in the template.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This requirements file contains natural-language comments exclusively in Chinese, including the title and dependency descriptions. Under the policy rule for language or locale constraints, this can be a violation because it imposes a specific language on users without any opt-in or documented region-specific justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown template forces a specific language/locale for all generated output through its headings and body text. The file does not indicate that Chinese is optional, user-selected, or required for a region-specific use case, which may violate language-choice policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

Natural-language policy violations include forcing a specific language without user opt-in. This template is fully Chinese-language and provides no indication that users may choose another language or that the locale restriction is intentional and documented.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown template presents all headings, labels, and instructions in Chinese only, which imposes a specific language on users. Under the policy, a forced language without user opt-in is a natural-language policy concern unless the locale constraint is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.