T08 · Insecure Dependencies
Warning
- Location
README.md:60- Finding
Unpinned MCP Dependency Creates Supply-Chain Exposure
- Content
View full analysis
- Remediation
View remediation
Security audit
TM Soil Moisture Skill
Security checks for vulnerabilities and agentic risk
Overview
The skill is a coherent local agriculture data reader with no evidence of hidden execution, exfiltration, persistence, or destructive behavior, but users should treat its advice and dependency setup cautiously.
Install only in an isolated environment, pin the mcp dependency, and connect it only to the intended local agriculture database. Treat returned sensor values and irrigation advice as decision support, not automatic control, especially because weather is simulated and database-derived values are not validated.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (2)
T09 · Insecure Skill Coding Practices
Warning
- Location
pico_claw_brain.py:40- Finding
Unvalidated Sensor Fields Are Exposed to the AI Tool Context
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The README states that the skill combines local sensor and geolocation data with external weather data, but it does not clearly disclose what data may be transmitted, under what conditions, or to which service. In an agricultural setting, device coordinates and field conditions can reveal sensitive operational information, so silent or under-documented sharing creates a real privacy and data-governance risk.
- Content
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 90% confidence
- Finding
The skill instructs the agent to connect to a local SQLite database and references weather/real-time data retrieval behavior, but it does not declare any explicit tool scope such as permissions or allowed-tools. Missing tool restrictions can let the runtime grant broader-than-necessary network or execution capabilities, increasing the blast radius if the skill is abused or prompt-injected.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The manifest description and role instructions require operation in Chinese and do not indicate that the user may choose another language. This is a natural-language policy concern because it forces a locale/language preference without explicit opt-in or documented justification.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
This code returns user-facing messages, help text, and tool descriptions entirely in Chinese, which effectively forces a specific language on users. The file does not provide a language/locale option or state that the skill is intentionally limited to a Chinese-speaking or region-specific environment.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The skill advertises intelligent irrigation support based on multi-depth soil temperature and humidity data, but the implemented logic only averages 20cm and 40cm humidity and ignores temperature and other depths. This mismatch creates unsafe overconfidence in the recommendation quality, which is especially risky in a precision-agriculture context where decisions may depend on deeper soil conditions and thermal state.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The function claims to incorporate future weather trends into irrigation advice, but it uses hard-coded simulated values instead of any real forecast input. In an agricultural decision-support skill, this can mislead users into trusting recommendations that ignore impending rainfall or drought conditions, potentially causing crop stress, water waste, or operational harm.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
The natural-language instructions and operational guidance are entirely in Chinese, which can amount to a language policy issue when no user opt-in or alternative language is offered. The file does not state that the skill is intentionally limited to Chinese-speaking operators or a region-specific deployment context.
- Content
Rp1
Low
- Category
- MCP Rug Pull
- Confidence
- 60% confidence
- Finding
pip install without ==version installs the latest release, which could include malicious changes.
- Content
Static analysis
No suspicious patterns detected.