Back to skill

Security audit

Home Appliance Analyst (家电行业分析师)

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only home-appliance analysis skill with no executable code or persistence, though users should verify its safety and regulatory advice before relying on it.

Install only if you want a Chinese-language home-appliance analyst/reference skill. Treat product safety, medical-adjacent, chemical disinfectant, UVC, privacy, and compliance outputs as research drafts and verify them against manuals, official standards, qualified professionals, and current regulations.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (18)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill’s top-level description is extremely broad and can trigger on many ordinary appliance-related questions without clear boundaries. Over-broad activation can cause unintended routing, increasing the chance that unrelated user prompts are handled under this skill’s assumptions, which may degrade safety, relevance, and compliance behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The manifest description and the entire operational guidance are written as a Chinese-only skill specification, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger keyword lists include generic terms such as market, analysis, price comparison, or compliance-related phrases without disambiguation or negative examples. This can cause false activations on routine consumer, shopping, or general research questions and route them into workflows that assume industry-analysis scope.

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 content recommends specific electric blanket types for pregnant women and infants, which is sensitive health- and safety-related guidance. In this skill context, users may rely on the recommendation as quasi-expert advice, but the statement lacks medical qualification, risk caveats, and direction to follow product labeling or consult a clinician, creating potential harm if the advice is wrong or overgeneralized.

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.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file describes APP remote answering, remote unlocking, facial recognition entry, and cloud-stored visitor records, all of which can affect physical security and personal privacy. The skill text presents these capabilities as product features but does not warn users about risks such as unauthorized access, biometric data sensitivity, or cloud data exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document gives procedural guidance for producing and using electrolyzed disinfectant while presenting broad safety and efficacy claims, but it omits key warnings about chlorine-containing off-gassing, improper concentration, skin/eye irritation, ventilation, storage instability, and the danger of mixing with acids or other cleaners. In a consumer-facing home-appliance analysis skill, this can encourage unsafe household chemical preparation and misuse under the appearance of expert guidance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The statement that the electrolysis process has 'no dangerous gas release' is unsafe because electrolysis of salt water can produce hydrogen and, under some conditions or faulty designs, chlorine-containing gases. Presenting the absence of gas hazard as a purchasing criterion without caution may cause users to operate such devices in poorly ventilated spaces or to underestimate failure and misuse risks.

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

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains only Chinese-language content and does not provide any user opt-in, alternative language option, or justification that it is intended solely for a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document gives product selection and usage-scenario guidance for heaters, which are inherently safety-sensitive appliances, but it does not include a clear consolidated warning about burn, fire, placement, ventilation, child/pet supervision, or avoiding coverage/nearby combustibles. In this skill context, users may rely on the material for purchase and use decisions, so omission of basic safety guidance can contribute to unsafe operation even though the content is not overtly harmful.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file's natural-language content is entirely in Chinese, and there is no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. Under the policy rule, forcing a specific language without user 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
89% confidence
Finding

This markdown file contains all user-facing content in Chinese and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file lists '录音电话' with stored messages and 'AI录音转写' that converts call content to text, both of which affect user privacy and potentially third-party consent. Under the markdown-specific warning criterion, the description omits any caution about recording, transcription, or legal/privacy implications.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The document promotes 'UVC杀菌' as a product capability but provides no warning about eye/skin exposure risks, proper shielding, or the difference between integrated enclosed UVC systems and direct user exposure. In a consumer home-appliance knowledge base, this omission can mislead users or downstream generated advice into treating UVC as universally safe, increasing the chance of unsafe handling or unsafe product recommendations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This file presents all guidance exclusively in Chinese and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without user 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
86% confidence
Finding

The entire skill file is written as a report template in Chinese and specifies report structure and output norms only in Chinese, with no indication that users may choose another language. Under the policy rules, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.