ClawHub
Back to skill

Security audit

Gardening Calendar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward gardening calendar helper with only minor locale-style caveats.

Install is reasonable for gardening advice. For non-UK gardening, specify your country or climate zone and preferred units so advice does not default to UK assumptions.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The file instructs the skill to speak like a professional UK allotmenteer and to use Celsius and UK metrics as a blanket rule. Because the skill also supports international contexts, these instructions impose a specific locale without clear user opt-in or justification.

Natural-Language Policy Violations

Low
Confidence
90% confidence
Finding
The instruction to write in the "SowTimes" style as direct, sophisticated, and UK-focused imposes a locale-specific presentation by default. This can conflict with the policy against forcing a specific language or locale when the user has not opted into that preference.

Static analysis

No suspicious patterns detected.