Security audit

Plant Identifier

Security checks for vulnerabilities and agentic risk

Overview

This plant-identification skill is a coherent local note-taking aid with disclosed storage and no evidence of hidden network, credential, or privileged behavior.

Before installing, decide whether you want the skill to save local plant observation notes and how broadly it should activate. Avoid storing precise home addresses in plant logs, and keep edible, toxic, or medicinal decisions separate from photo-based identification.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (1)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The skill leaves future activation boundaries intentionally open-ended, asking whether it should activate for broad categories like mystery plants, weeds, houseplants, and possibly plant care questions. In an agent setting, ambiguous activation criteria can cause the skill to trigger outside its intended scope, leading to unnecessary data access, user confusion, or interference with other skills and safety policies.

Static analysis

No suspicious patterns detected.