Back to skill

Security audit

Garden Planner

Security checks for vulnerabilities and agentic risk

Overview

This garden-planning skill is purpose-aligned and transparent about its local garden file and Open-Meteo weather lookup.

Before installing, understand that weather and ZIP-based frost checks contact Open-Meteo with your location or coordinates, and that plant and watering records are saved locally under the disclosed garden data directory unless you override it.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

This variant of the mismatch finding includes undeclared external weather/geocoding API access, which creates a real security concern when combined with absent permissions. Hidden or insufficiently disclosed network behavior can expose location-related data and violate user expectations about what a gardening skill transmits externally.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

This variant of the mismatch finding includes undeclared external weather/geocoding API access, which creates a real security concern when combined with absent permissions. Hidden or insufficiently disclosed network behavior can expose location-related data and violate user expectations about what a gardening skill transmits externally.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

This variant of the mismatch finding includes undeclared external weather/geocoding API access, which creates a real security concern when combined with absent permissions. Hidden or insufficiently disclosed network behavior can expose location-related data and violate user expectations about what a gardening skill transmits externally.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

This variant of the mismatch finding includes undeclared external weather/geocoding API access, which creates a real security concern when combined with absent permissions. Hidden or insufficiently disclosed network behavior can expose location-related data and violate user expectations about what a gardening skill transmits externally.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill advertises scripts that write local state to garden.json and perform network access for weather lookup, but it declares no permissions or allowed-tools scope. Missing capability scoping weakens least-privilege controls and can let a seemingly harmless gardening skill gain broader file-write or network behavior than users and policy engines expect.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger terms are broad enough to activate on ordinary gardening conversation, increasing the chance the skill runs unintentionally. Over-broad invocation expands exposure to its file-write and network behaviors, causing unnecessary data access or external requests in contexts where the user did not intend to use this skill.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/weather_check.py (reported line 18)May include surrounding context.

python
import urllib.error
from datetime import datetime, date, timedelta

FORECAST_URL = "https://api.open-meteo.com/v1/forecast"
GEOCODE_URL = "https://geocoding-api.open-meteo.com/v1/search"

FROST_THRESHOLD_C = 0.0       # 32°F

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The geocoding request hard-codes language: "en", which imposes a specific language/locale in returned place names. This is a natural-language policy concern because the skill does not offer user opt-in or explain why English-only output is required.

Content

No source excerpt is available for this finding.