Back to skill

Security audit

Phase-Locked Loop Parameter Tuning (锁相环参数整定)

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed PLL calculation skill with some usability and accuracy caveats, but no evidence of malicious or high-impact system behavior.

Before installing, treat it as a specialized Chinese-language engineering calculator. Confirm Unom, grid frequency, and damping ratio explicitly before relying on results, especially for non-690 V or 60 Hz systems.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger definition matches on very broad technical keywords such as 'PLL', 'PI参数', and '自然频率', which can appear in many unrelated contexts. This can cause the skill to activate unintentionally, injecting domain-specific assumptions or calculations into conversations where the user did not request this tool, reducing reliability and potentially contaminating other tasks.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill contains contradictory instructions about whether Unom must be explicitly collected before calculation. In an agent setting, this inconsistency can cause silent use of an incorrect voltage assumption, producing materially wrong engineering outputs that may mislead PLL tuning or validation workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The markdown states a default of f0 = 50 Hz and labels it as the China/Europe standard, which bakes in a region-specific assumption. Because this is natural-language guidance and not clearly framed as requiring user confirmation for locale-specific systems, it risks applying a locale convention without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This file contains natural-language comments and printed output entirely in Chinese, including the function description, parameter documentation, and console messages. Under the policy rule, forcing a specific language without user opt-in can be a locale-policy violation when no alternative language option or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This skill file contains natural-language comments, parameter descriptions, examples, and printed output in Chinese only. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The fprintf messages shown to users at runtime are all Chinese-language strings. This creates a locale/language constraint in the skill's behavior without giving users a choice or documenting a justified regional limitation.

Content

No source excerpt is available for this finding.