Back to skill

Security audit

Performance Monitoring

Security checks for vulnerabilities and agentic risk

Overview

This skill is a performance-monitoring guide that records operational metrics and alerts, with no evidence of hidden execution, exfiltration, or destructive behavior.

Before installing, confirm what metrics will be sent to Feishu, who can access those tables or alerts, and whether OpenClaw logs or memory metadata may contain sensitive workflow information. Scope the log directory and retention settings to your environment.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly collects operational metrics and records them to logs and Feishu tables, but provides no warning, scoping, minimization, or handling guidance for potentially sensitive operational data. In an agent environment, performance logs can contain timestamps, task outcomes, retry/fallback behavior, and possibly identifiers or workflow metadata that may be exposed to external systems or unauthorized viewers.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file mixes some English labels with predominantly Chinese operational documentation and does not indicate that users may choose their preferred language or that the skill is intentionally region-specific. This can violate a language/locale policy when a specific language is effectively forced without opt-in or justification.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documentation says metrics are recorded to logs/performance-metrics-YYYY-MM-DD.json, implying date-partitioned log files. However, the PowerShell implementation writes to performance-metrics.json via the MetricsFile default and Out-File, which contradicts the documented storage behavior and retention model.

Content

No source excerpt is available for this finding.