ClawHub
Back to skill

Security audit

Henteplan Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward waste-collection lookup helper with optional user-directed reminders, but users should understand that it may store location-related schedule identifiers.

Before installing, be aware that using this skill may involve sending your address query to henteplan.no and saving a provider/locationId for future lookups. Only set up the optional daily reminder if you want recurring OpenClaw automation, and review or remove the cron/HEARTBEAT entry if you no longer need it.

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

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill expands from simple waste-schedule lookup into cron-based automation that can trigger recurring actions and notifications. While the documented cron command is not obviously malicious, adding persistence and scheduled execution increases the skill’s operational scope and risk surface beyond the stated purpose, especially if users are encouraged to embed identifiers and recurring prompts without clear consent, review, or security guidance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill advises remembering the user’s provider and locationId for future queries without warning that these values can function as persistent household location metadata. Although not highly sensitive by themselves, they can help correlate a user to a specific address or service location, especially when combined with address searches and schedule data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.