Back to skill

Security audit

Plant Care Expert

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language plant identification and care guide with no executable code, persistence, or hidden data access, though users should treat pesticide advice cautiously.

Install only if you want a Chinese-language plant-care helper. For pesticide, fungicide, fertilizer, or toxic-plant advice, verify against product labels and local rules, use appropriate protection and ventilation, and keep chemicals and toxic plants away from children and pets.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (12)

Harmful Content Injection

Critical
Category
Prompt Injection
Confidence
70% confidence
Finding

This content may contain harmful instructions that could cause physical harm if followed. CRITICAL: Review carefully before use.

Content

Scanner excerpt · references/plant_database.md (reported line 439)May include surrounding context.

md
### 龟背竹(Monstera deliciosa)

- 毒性:草酸钙结晶,误食引起口腔不适
- 处置:告知家人勿食,放在安全位置

### 夹竹桃(Nerium oleander)

- 毒性:全株有毒,误食可致命
- 处置:强烈不建议室内养护

### 水仙(Narcissus)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
---
AIGC:
    ContentProducer: Minimax Agent AI
    ContentPropagator: Minimax Agent AI
    Label: AIGC
    ProduceID: "00000000000000000000000000000000"
    PropagateID: "00000000000000000000000000000000"
    ReservedCode1: 3044022034cadbaf26f4d65c387fa907e8de83aeb60c5cf52175c0a4c92321938257016302202784e00a7ba61b818c1e466efbac648a37eb69e86a7248cae634a23c267e8835
    ReservedCode2: 3045022100936396d2abe46c36df94a1f33fbc0c1717bb4f86225fbd038adab333b478906c022007f03738a36b53b9ff3f995e3d1c73bcf5bc33c45dbf52dd744d40d05adb7635
author: MiniMax Agent AI
description: 植物识别与养护专家技能。当用户发送植物图片或询问植物名称时触发。支持:1) 识别植物种类 2) 评估养护难度 3) 提供详细养护指南 4) 诊断植物问题 5) 给出急救建议。适用于室内外绿植、花卉、

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language instructions and examples are entirely in Chinese, which effectively imposes a language choice on users. The file does not state that the skill is China-region-specific or otherwise justify the locale restriction, nor does it offer multilingual or opt-in language behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documented trigger conditions are overly broad, including generic plant-related questions and any plant image, which can cause the skill to activate in situations where the user did not clearly request this specialized behavior. Unintended invocation can override more appropriate routing, reduce user control, and create privacy or safety issues if images or health-related plant concerns are automatically processed without sufficient specificity.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest description, invocation examples, and user interaction guidance are entirely in Chinese, with no indication that other languages are supported or that Chinese is a justified regional requirement. This can constitute a language-policy issue because the skill implicitly forces one language without offering user choice or opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases at these lines are common conversational Chinese phrases that can appear in many ordinary plant or even broader household discussions, which increases the chance of unintended skill activation. Overbroad activation can route users into this skill without clear intent, causing context hijacking, irrelevant guidance, or interference with higher-priority skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger on this line is excessively broad for a skill manifest and is likely to collide with normal gardening conversation. This can cause accidental invocation and poor skill routing, which is a security-relevant integrity issue in multi-skill agent systems because user intent may be misinterpreted.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The troubleshooting guide recommends pesticides and chemical agents such as 吡虫啉、啶虫脒、阿维菌素、马拉硫磷、多菌灵、百菌清、硫磺粉 and chemical salts/fertilizers without any safety guidance, dilution cautions, PPE advice, ventilation requirements, storage warnings, or child/pet protections. In a consumer-facing plant-care skill, users may directly follow these instructions at home, creating avoidable poisoning, skin/eye exposure, inhalation, or misuse risks.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
97% confidence
Finding

The trigger '养花' is extremely short and generic, making it prone to matching unintended user input. In agent ecosystems, very short triggers can lead to false activations, reduced routing integrity, and easier trigger collision with unrelated or only loosely related requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains user-facing content exclusively in Chinese, beginning with the title and description, and nowhere offers an alternative language or user opt-in for locale. 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.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file is entirely written in Chinese and presents the plant knowledge base only in that language, with no indication that users can select another language or that the Chinese-only constraint is required for a region-specific purpose. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing instructions in the skill content are presented only in Chinese, with no indication that the user can choose another language or that the locale restriction is intentional and justified. This matches the policy category for language or locale constraints imposed without explicit user opt-in.

Content

No source excerpt is available for this finding.