ClawHub
Back to skill

Security audit

Sensibo

Security checks for vulnerabilities and agentic risk

Overview

This Sensibo AC skill is purpose-aligned, but it needs review because it asks users to store an API key in plaintext and enables real device and schedule changes without clear confirmation safeguards.

Install only if you are comfortable giving the agent control over your Sensibo devices. Store the API key in a protected secret store or environment variable instead of TOOLS.md, avoid logging expanded curl commands, and require confirmation before deleting schedules, changing automations, or applying bulk device changes.

A.I.G

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:16
Finding

Plaintext Storage and URL Exposure of Sensibo API Credentials

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
95% confidence
Finding

The skill instructs the operator to obtain an API key and store it in TOOLS.md, a markdown file that is likely to be broadly readable, accidentally committed, or exposed to other tools and prompts. This creates a clear credential-handling weakness: compromise of that file would give an attacker direct control over the user's Sensibo devices and access to device metadata.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

First-Time Setup

  1. Get API key from https://home.sensibo.com/me/api
  2. List devices to get IDs:
    bash
    curl --compressed "https://home.sensibo.com/api/v2/users/me/pods?fields=id,room&apiKey={API_KEY}"

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says the skill triggers on phrases like "how hot is it" and "set bedroom to 22," which are ambiguous outside a clearly scoped smart-home context. The file does not provide exclusion conditions or negative examples to prevent unintended invocation from common conversational phrases.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill documents state-changing and destructive actions such as powering devices on/off, changing climate settings, and deleting schedules without requiring confirmation or warning for impactful operations. In an agent setting, overly direct execution of these actions increases the risk of unintended real-world changes from ambiguous user requests or accidental invocation.

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 · SKILL.md (reported line 37)May include surrounding context.

Turn ON/OFF

bash
curl --compressed -X POST "https://home.sensibo.com/api/v2/pods/{device_id}/acStates?apiKey={key}" \
  -H "Content-Type: application/json" -d '{"acState":{"on":true}}'

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 · SKILL.md (reported line 91)May include surrounding context.

Include measurements in fields:

bash
curl --compressed "https://home.sensibo.com/api/v2/pods/{device_id}?fields=measurements&apiKey={key}"

Response includes:

Static analysis

No suspicious patterns detected.