Security audit

WeChat Article Fetcher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple WeChat article extraction guide; its archiving step should be user-confirmed, but the artifacts do not show hidden, destructive, or deceptive behavior.

Install only if you want an agent to help extract and summarize WeChat articles. Before using the archive step, confirm whether content should be stored locally or in Feishu, and avoid saving private or copyrighted full text unless you have permission or a clear internal-use need.

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

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

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The invocation description includes broad language like 'fetch and archive WeChat articles for reference,' which can cause the skill to trigger for generic archiving or content-handling tasks beyond the narrowly intended mp.weixin.qq.com extraction use case. Over-broad routing increases the chance the agent applies this skill in contexts involving unnecessary collection, retention, or processing of third-party copyrighted or sensitive content.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill instructs the agent to save fetched article content to Feishu documents or local markdown without requiring a user warning, confirmation, or data-sensitivity check. This can lead to unintentional exfiltration, over-retention, or storage of copyrighted/private content in external systems or local files that the user did not explicitly approve.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The skill content and operational guidance are presented entirely in Chinese without indicating that language choice should follow user preference. This can create a language or locale policy issue if the skill assumes Chinese interaction rather than offering or documenting user language selection.
Content: No source excerpt is available for this finding.