Back to skill

Security audit

系统化调试

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward debugging guide and code example, with only minor usability caveats around broad activation words and Chinese-language presentation.

Install this if you want a Chinese-oriented systematic debugging workflow. Be aware that generic trigger words like debug may activate it broadly, so prefer invoking it explicitly when you want this workflow.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The description is written to prescribe Chinese-language behavior without any indication that this is conditional on user preference. Forcing output language without explicit opt-in can override user intent, create accessibility/usability issues, and in multi-skill environments may cause the model to ignore the user's requested language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation phrases "调试 / debug / 排查问题" are broad, common terms that can appear in ordinary conversation, increasing the chance this skill activates when the user did not intend to invoke it. In an agent setting, accidental activation can steer responses into the skill's prescribed workflow, causing prompt-routing confusion and reducing reliability, even though the skill content itself is not otherwise overtly harmful.

Content

No source excerpt is available for this finding.