Back to skill

Security audit

每日早报

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a simple daily brief by fetching public weather and V2EX data, with no evidence of hidden, destructive, or credential-seeking behavior.

Before installing, confirm you want a Chinese daily brief focused on Nantong weather and V2EX hot topics. If using a scheduler, configure it deliberately so it runs only at the intended time and does not interrupt normal conversations triggered by broad phrases.

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 phrases include very generic expressions like “早报” and “今天怎么样”, which can overlap with normal conversation and cause the skill to activate unintentionally. In a scheduled/execution-oriented skill that uses exec and external network calls, accidental triggering increases the chance of unnecessary command execution, user confusion, and unintended data retrieval.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill content is primarily in Chinese but also includes fixed English phrasing such as section labels and time notation, with no statement that the user can choose output language or locale. This can conflict with a language/locale policy requiring user opt-in rather than implicit language assumptions.

Content

No source excerpt is available for this finding.