Back to skill

Security audit

安全审计

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown-only security audit skill with broad but disclosed read, command, and write capabilities and no evidence of hidden execution, persistence, or exfiltration.

Install only for audits of repositories, infrastructure descriptions, or agent systems you are authorized to inspect. Give the agent a narrow target_path and audit_scope, review any proposed shell commands before execution, and avoid providing secrets unless they are necessary for the audit.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description uses very broad activation language such as 'use when security detection, compliance audit, vulnerability scanning, encryption protection' without clear boundaries, required confirmations, or target constraints. In an agent context, this can cause over-invocation on sensitive repositories, URLs, or infrastructure and may trigger read/exec/write-capable workflows in situations where a narrower skill should not run.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description states '支持中文交互' as a capability, and the document consistently presents the skill as Chinese-interaction oriented without offering an opt-in or alternative language choice. This can violate language/locale policy when a skill appears to force or default to a specific language without user selection.

Content

No source excerpt is available for this finding.