Back to skill

Security audit

智能需求解读器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a self-contained requirement analysis helper with some disclosure gaps around activation and process-local logging, but no evidence of exfiltration, credential access, remote execution, or destructive behavior.

Install only if you want a mostly Chinese-language requirement-analysis workflow. Avoid placing secrets or regulated data in prompts unless you are comfortable with the skill keeping recent requirements in process memory during a run; maintainers should document or remove that logging and make auto-activation more explicit.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (25)

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding

If the implementation writes a local file such as interview_framework.json without declaring that side effect, it introduces undeclared persistence and possible leakage of user-derived requirement data. Hidden write behavior is more dangerous in this context because requirement gathering often includes confidential operational, product, or customer information that users do not expect to be stored.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

If the implementation writes a local file such as interview_framework.json without declaring that side effect, it introduces undeclared persistence and possible leakage of user-derived requirement data. Hidden write behavior is more dangerous in this context because requirement gathering often includes confidential operational, product, or customer information that users do not expect to be stored.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding

If the implementation writes a local file such as interview_framework.json without declaring that side effect, it introduces undeclared persistence and possible leakage of user-derived requirement data. Hidden write behavior is more dangerous in this context because requirement gathering often includes confidential operational, product, or customer information that users do not expect to be stored.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The automatic trigger condition 'when the requirement description is vague' is subjective and broad, which can cause the skill to activate unexpectedly during ordinary conversations. In an agent environment, overly broad auto-invocation increases the chance of unintended interception of user prompts and can disrupt routing, override user intent, or expose unnecessary context to the skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manual invocation phrase '帮我详细分析这个需求' is generic enough to overlap with normal user requests, so the skill may be invoked when the user is simply asking for analysis rather than explicitly choosing this skill. This can lead to accidental execution, confusing behavior, and unintended processing of user content under the skill's workflow.

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.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

文件中的自然语言描述整体以中文固定表述技能行为,但未说明这是面向特定中文场景的限定,也未提供用户可选择其他语言或按用户语言回复的选项。根据规则,强制特定语言而无用户选择可能构成语言/区域政策问题。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

该 markdown 文件适用 SQP-1。'需求描述模糊'、'复杂度高'、'需求紧急' 等触发条件覆盖大量日常请求,但未说明技能何时应激活、何时不应激活,也没有列出明确触发短语或排除示例,容易导致非预期调用。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file presents the skill content entirely in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file contains user-facing natural-language guidance only in Chinese, beginning with the Chinese title and instructions for how to prepare requirements for AI consumption. Under the policy rule, forcing a specific language without user opt-in can be a locale-policy violation when no alternative language option or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire template and its instructions are written exclusively in Chinese, and the document does not indicate that Chinese is optional or that the template is intended only for a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown template forces a specific language/locale for all users through its headings and field labels, and there is no indication that Chinese is optional or that the template is intended only for a Chinese-speaking or region-specific context. Under the policy, fixed language requirements without user opt-in or clear justification are a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains user-facing natural-language strings such as the module description, usage text, and printed results entirely in Chinese. Under the policy rule for language/locale, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code file contains natural-language descriptions and user-facing report strings that assume Chinese as the only interaction language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The generated classification report uses only Chinese headings, labels, and recommendations, which constrains the user experience to a single language. The policy allows locale-specific behavior only when users are given a choice or the restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Natural-language strings throughout the file, including enum values, prompts, comments, and printed output, are fixed in Chinese. There is no indication that users can choose another language or that this locale restriction is documented as an intentional region-specific constraint.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The interpreter retains natural-language user inputs in memory and later returns recent_interactions from get_learning_insights, creating a direct data exposure path. In the context of a requirement-interpreter skill, users are especially likely to submit confidential project requirements, roadmap details, or regulated business data, making this retention-and-echo behavior more dangerous than in a trivial chat utility.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill stores raw user requirement text in self.interaction_log along with derived metadata and timestamps without consent, minimization, or any retention controls beyond an in-memory cap. Requirement text can easily contain sensitive business plans, customer data, credentials, or internal project details, so retaining and re-exposing it increases confidentiality risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This code file contains docstrings, question prompts, and printed messages exclusively in Chinese, which imposes a specific language on users. The policy allows fixed locale behavior only when a language choice is offered or the regional/language constraint is clearly justified, neither of which appears here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The entire skill documentation is presented only in Chinese, with no indication that users may choose another language or locale. This can be a language/locale policy concern when the skill implicitly requires a specific language without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This JSON case library uses Chinese titles, descriptions, requirements, and questions throughout, but provides no natural-language indication that the skill is Chinese-only or that users can opt into another language. Under the language/locale policy, forcing a specific language without user choice can be a policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This Python file contains natural-language descriptions and console output in Chinese, beginning with the module docstring and continuing throughout the skill metadata. Under the policy rule for language/locale, forcing a specific language without user opt-in can be a violation when no justification or alternative is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The test/output function prints all user-visible messages in Chinese and does not provide any mechanism to choose another language. This is a natural-language locale policy concern because the runtime interaction assumes a single language without documented justification.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest describes a skill for interpreting user requirements and providing standardized deliverables; that purpose does not inherently require filesystem path construction and file loading logic in the exposed test flow. While loading a bundled case library is plausibly supportive of case matching, the code adds an undeclared local file access capability beyond the core semantic task described in the manifest.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest describes a requirement-interpretation skill that helps users express needs and provides standardized deliverable lists. In this file, the main execution path persists data to a local file (interview_framework.json), which is a state-changing behavior not implied by the description of a conversational/interpreting skill.

Content

No source excerpt is available for this finding.