Back to skill

Security audit

公众号内容聚合

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to match its stated purpose: summarizing WeChat public-account content, remembering topic preferences, and saving to Feishu only after user confirmation.

Before installing, be aware that this skill may remember your selected content keywords and attempt daily pushes. Use it only if you are comfortable with those preferences being stored, and confirm Feishu saves only when you want records added to the content aggregation library.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough to overlap with ordinary user requests about following or organizing public account content, which can cause the skill to activate unintentionally. In an agent environment, overbroad activation can redirect user intent, invoke external search/storage flows, and create privacy or integrity issues through unwanted data handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrases are broad enough to overlap with ordinary user requests, which can cause the skill to activate unexpectedly. In this skill, unintended activation matters because it can lead to web searches, memory writes, and downstream storage prompts without the user explicitly intending to invoke an automation workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill describes daily scheduled pushes and recording user keyword preferences into memory, but it does not provide clear notice about data retention, persistence, review, or revocation. This creates a privacy and consent risk because users may not understand that their preferences are being stored and used for recurring automated behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The entire skill description and user-facing trigger/instruction language are presented only in Chinese, with no indication that users may choose another language. Under the stated policy, a language constraint should either be optional for the user or clearly documented as justified for a region-specific tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

文件中的说明、触发词和交互文案均固定为中文,未见向用户提供语言或 locale 选择的描述。若该技能面向通用用户环境,这种默认强制单一语言可能构成语言/locale 策略问题。

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The flow section says the final result should be pushed in copywriting/prose form and explicitly says 'not a table' (L35), but the output format section immediately defines a table layout (L39-L42). This is an active contradiction in the skill documentation about what the skill is supposed to produce.

Content

No source excerpt is available for this finding.