Back to skill

Security audit

A Stock Daily Review

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently generates an A-share daily market review, with expected data lookups and a disclosed local Markdown report output.

Install this if you want automated A-share daily review reports and are comfortable with it calling market-data/web tools and writing reports under E:/文件/workbody/. Consider asking for confirmation before overwriting an existing same-day report, and use A-share-specific phrasing when invoking it.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrase “生成今日复盘” is generic enough that it may match ordinary requests that do not clearly imply consent to invoke this specific skill. Because the skill performs external data access and writes a file to disk, accidental activation can cause unintended side effects and privacy/workflow disruption even without malicious user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is designed to write a Markdown report to a fixed local path on the host system without clearly disclosing this side effect in the activation description. This can lead to unauthorized or unexpected local file creation, overwriting of existing files, or leakage of sensitive workflow details about the host filesystem if the skill is triggered unintentionally.

Content

No source excerpt is available for this finding.