Security audit

Argument Audit

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a local argument-analysis tool, but it explicitly encourages exporting workplace WeChat chat records without privacy or consent safeguards.

Review before installing if you may use it on private or workplace conversations. Provide only short, relevant excerpts, redact names and company details, and avoid sharing third-party or confidential chat logs unless you have authorization.

A.I.G

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

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The README explicitly suggests exporting WeChat chat records for analysis, which can involve sensitive personal, workplace, or third-party data, yet it provides no privacy warning, consent guidance, or data-minimization instructions. In the context of an argument-analysis skill, this omission increases the risk that users will upload confidential conversations without considering legal, ethical, or organizational privacy constraints.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly suggests exporting WeChat chat records for analysis without any privacy warning, data-minimization guidance, or consent checks. Chat logs commonly contain personal, confidential, or third-party information, so encouraging bulk export creates a clear risk of unnecessary disclosure and downstream mishandling of sensitive data.
Content: No source excerpt is available for this finding.

Ssd 3

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The instruction to export private WeChat chat records is a natural-language prompt for users to disclose sensitive data into the analysis flow. In this context, the danger is elevated because workplace arguments in chat groups often include employee names, internal project details, business discussions, and personal messages involving non-consenting third parties.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This Python file contains user-facing natural-language strings entirely in Chinese, including the module description, error messages, audit output, and CLI usage example. Because the skill does not offer any language/locale selection or explain that it is intentionally limited to Chinese-speaking users, it violates the language/locale policy for natural-language behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This manifest file says to use the skill when a user asks about several analysis topics 'or wants to analyze the strength and validity of an argument.' That catch-all condition is broad and lacks explicit scope limits or negative examples, which could cause unintended invocation for general analytical conversations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The file includes Chinese-language title text and two example user interactions entirely in Chinese, while other sections are in English. This can imply a language expectation or default without explicitly offering the user a choice or documenting that the skill is intended for a Chinese-speaking context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The description centers invocation on Chinese phrases such as '论点分析、论证评估、逻辑审查、观点评估' even though the rest of the skill is largely bilingual/English. This may constitute a language/locale policy issue because no user choice or explicit justification for a Chinese-only trigger preference is provided.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The natural-language description includes Chinese trigger phrases and a Chinese title, but the manifest does not explain whether the skill is intended only for Chinese users or whether language selection is optional. This can violate language/locale policy expectations when a skill appears to privilege a specific language without user opt-in or justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.