Back to skill

Security audit

A股客户会前准备助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed A-share investor meeting brief generator that uses public market data and does not include executable code, persistence, or hidden data handling.

This appears safe to install for A-share investor meeting preparation. Users should be aware that broad triggers may activate it for nearby finance research requests, and they should confirm before syncing any generated brief to Tencent Docs or sharing it with a team.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
91% confidence
Finding

The trigger at line 14 is broad enough to match many ordinary finance workflows, which can cause this skill to activate when the user did not explicitly request it. In an investment-research context, unintended activation can lead to unnecessary retrieval, generation of sensitive meeting-prep content, and misrouting of user intent to a domain-specific skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger on line 17 is too generic for the target domain and is likely to overlap with routine user requests that are not intended to invoke this specific skill. This increases the chance of accidental invocation, which is especially risky here because the skill performs structured financial profiling and meeting-preparation actions that may not fit the user's actual request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger on line 19 is ambiguous and commonly used in broader research or client-background discussions, so it may activate outside the intended scope of investor meeting preparation. In this skill's context, that creates a real prompt-routing weakness: users discussing general customer background could unintentionally invoke a workflow that aggregates company, holdings, and meeting-briefing content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.