Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md python3 scripts/garden_doctor.py diagnose \
Security audit
garden-doctor
Security checks for vulnerabilities and agentic risk
Overview
This plant-care skill is a local diagnostic helper that matches symptoms to garden problems and does not show hidden access, persistence, network use, or data exfiltration.
Install only if you are comfortable running a local Python CLI for plant diagnosis. Treat treatment recommendations as general gardening information, especially chemical controls: follow product labels, use appropriate protective gear and ventilation, and keep chemicals 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
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md python3 scripts/garden_doctor.py diagnose \
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md python3 scripts/garden_doctor.py diagnose \
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md python3 scripts/garden_doctor.py diagnose \
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md python3 scripts/garden_doctor.py diagnose \
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 89% confidence
- Finding
The skill documentation shows shell-based usage (
python3 scripts/garden_doctor.py ...) but the manifest does not declare any explicit tool restrictions such aspermissionsorallowed-tools. In an agent ecosystem, undeclared shell capability can cause the runtime or reviewer to underestimate what the skill may invoke, increasing the risk of unintended command execution or over-privileged operation if the backing code is compromised or later modified.- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The knowledge base recommends chemical treatments such as copper fungicide, sulfur-based fungicide, bactericide, miticide, systemic insecticide, herbicide-related handling, and alcohol/soap/oil applications without any safety qualifiers, PPE guidance, dosage cautions, ventilation advice, pet/child warnings, or instructions to follow product labels. In a consumer plant-care skill, users may act directly on this guidance, increasing risk of misuse, plant damage, toxic exposure, or unsafe indoor application.
- Content
Static analysis
No suspicious patterns detected.