Back to skill

Security audit

daily-deals-1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple markdown-only daily deals notification guide with disclosed WeChat delivery, but users should confirm any recurring external delivery before enabling it.

Before installing or using this skill, confirm where reports will be sent, what data is included, how the WeChat destination is linked, and how to pause or cancel recurring pushes.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The example trigger '订阅每日神价推送,发送到我的微信' is broad and action-oriented, combining subscription setup with delivery to an external account without showing any confirmation or scoped activation rules. In an agent setting, this increases the risk of unintended enrollment or message forwarding if similar phrasing is interpreted automatically from casual user requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly offers to send reports to '我的微信' but does not warn users that deal reports, preferences, or history may be transmitted to an external messaging platform. This can cause privacy and account-linking risks because users may not understand that data leaves the agent environment and is delivered through a third-party channel.

Content

No source excerpt is available for this finding.