Back to skill

Security audit

Auto Agent 4974 F58bc0

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown tutorial skill with broad activation wording but no code, credentials, persistence, or sensitive access.

Before installing, understand that this skill may activate on fairly generic Notion or Chinese tutorial phrasing; otherwise it has no visible sensitive permissions or executable behavior.

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
93% confidence
Finding

The trigger phrase "一口气搞懂" is a generic conversational expression rather than a narrowly scoped invocation, so it can cause accidental activation during unrelated user interactions. In an agent-skill system, broad triggers increase the chance of unintended skill routing, which can confuse behavior, override more appropriate skills, or expose users to outputs they did not explicitly request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The activation condition "用户需要auto_agent_4974相关帮助" is ambiguous because it lacks objective matching criteria and leaves scope interpretation to the runtime or orchestrator. Ambiguous activation logic can cause over-triggering on loosely related requests, leading to unintended execution and reducing trust in agent routing boundaries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.