Back to skill

Security audit

PC Temperature Monitor

Security checks for vulnerabilities and agentic risk

Overview

This temperature checker needs review because an ambiguous command can launch administrator-level code from an unverified library in a temporary folder.

Require an explicit temperature-check request before elevation, and verify the sensor library in a protected location before loading it as administrator. Expect temporary reports to be replaced and some output to appear in Chinese. The review concern is execution control and library integrity, not evidence of malicious intent.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (5)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
Use `scripts/generate-html.ps1` to produce the colored HTML report and open it in the default browser.

The required output structure forces Chinese status text without user opt-in.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The skill requires an exact summary structure containing the Chinese prefix 温度总结 and Chinese temperature-status values. It provides neither a language choice nor a documented justification for requiring Chinese regardless of the user's language.

Content

No source excerpt is available for this finding.

The standalone trigger `temp` is ambiguous and immediately executes the full workflow.

Medium
Category
Trigger Abuse
Confidence
92% confidence
Finding

temp can refer to temporary files or a temporary directory rather than hardware temperatures. Treating it as an unconditional command can unintentionally launch the download and elevated sensor-query workflow.

Content

No source excerpt is available for this finding.

An existing output file is forcibly deleted without disclosure or confirmation.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The script silently deletes any existing file at the configurable $OutputFile path before collecting results. Although writing temperature results is expected, destroying prior file contents is not disclosed by a comment, warning, log, or confirmation prompt.

Content

No source excerpt is available for this finding.

The generated report forces Chinese-language output without a user language choice.

Low
Category
Output Handling
Confidence
94% confidence
Finding

The HTML template hardcodes Chinese headings, column labels, and summary labels; the temperature-status strings are also fixed in Chinese. The script offers no language or locale option and provides no documented justification for restricting the report to that language.

Content

No source excerpt is available for this finding.