Back to skill

Security audit

Power Electronics

Security checks for vulnerabilities and agentic risk

Overview

The skill is a local Chinese-language power-electronics reference and calculator with no evidence of hidden network access, persistence, credential theft, or destructive behavior.

Install this if you want a Chinese-language power-electronics assistant with local calculation scripts. Review the broad triggers and tool permissions first, and treat calculator outputs as engineering estimates that still need independent validation before real hardware use.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (20)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The code is clearly within the general domain of power electronics, but its actual scope is much narrower than the description. It only calculates DC-DC parameters for buck, boost, and buck-boost converters via a command-line script using standard formulas. There is no implementation for AC-DC rectifiers, PFC, DC-AC inverters, AC-AC converters, modulation methods like SPWM/SVPWM, multilevel/NPC topologies, or isolated converters such as Flyback/QR/LLC. It also does not include any Simulink assets or publishing/integration behavior. Because the declared description presents a substantially broader multifunction skill than the code actually provides, this is a material description-behavior mismatch.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The file consistently presents the skill name, description, workflow, output format, and usage guidance only in Chinese, and does not indicate that language selection is optional. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown/manifest file defines triggers such as "PFC", "QR", "整流", "逆变", "Buck", and "Boost" without any exclusion conditions or contextual limits. Several of these terms are short, generic, or widely used in electrical engineering contexts, which increases the chance of unintended invocation outside the specific power-electronics workflow.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and all instructional content are presented in Chinese, with no indication that users may choose another language or locale. Under the policy rules, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The title and core instruction text are written only in Chinese and direct the agent how to respond when users request simulations, but there is no indication that language choice is optional or limited to a justified region-specific context. This can violate language/locale policy when a skill effectively constrains output to a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring presents the skill name and usage description only in Chinese, which imposes a specific language on users. Under the policy, language-specific behavior should offer user choice or clearly justify the locale restriction, and no such opt-in or justification is provided here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The CLI help text and printed error messages are written exclusively in Chinese, which forces one language for all users. There is no mechanism for selecting another language and no documentation indicating that this is a region-specific tool with a justified locale constraint.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
70% confidence
Finding

Overly Broad Trigger: 'QR' is too short and may match unintended inputs

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
70% confidence
Finding

Overly Broad Trigger: '整流' is too short and may match unintended inputs

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
70% confidence
Finding

Overly Broad Trigger: '逆变' is too short and may match unintended inputs

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file is written entirely in Chinese and does not offer any language choice or indicate that the skill is intentionally limited to Chinese-speaking users. Under the policy criteria, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The document title and instructional text are written entirely in Chinese, including the directive that the agent should solve similar problems by following the steps. Under the policy rule, forcing a specific language without user opt-in is a natural-language locale violation when no alternative or opt-in is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file is entirely written in Chinese, beginning with the title on L001, and provides no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language text stating the skill outputs in Chinese, including the module docstring and Chinese-only user-facing messages. The policy category applies to all file types, and there is no indication that users can opt into another language or locale.

Content

No source excerpt is available for this finding.