ClawHub
Back to skill

Security audit

AirShelf Agentic Commerce Platform

Security checks for vulnerabilities and agentic risk

Overview

This shopping skill is coherent, but it needs Review because its shell examples can mishandle user search text and it under-discloses privacy considerations for sensitive searches and optional email use.

Review before installing. Use this only if you are comfortable sending product searches, including possibly health, family, or preference details, to AirShelf. Agents should URL-encode parameters or use a structured HTTP client instead of raw string substitution in shell commands, and should ask before checkout or before sending an optional email address.

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:36
Finding

Unsafe interpolation of user-controlled search queries into a shell command

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

Find products by natural language query. Returns structured data with Decision Packs.

bash
curl -s "https://dashboard.airshelf.ai/api/search?q=QUERY&limit=5" | python3 -m json.tool

Parameters:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation guidance is broad enough to trigger on generic shopping, recommendation, or problem-description requests, which can cause the agent to send user queries to an external commerce service without sufficiently narrow user intent. In this context, problem-based examples such as health- or baby-related needs increase the risk of transmitting sensitive preference or health-adjacent information to a third party unnecessarily.

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 62)May include surrounding context.

Example:

bash
curl -s "https://dashboard.airshelf.ai/api/search?q=natural+mosquito+repellent+for+babies&limit=3"

Step 2: Compare Products

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill invites collection of an optional customer email for checkout tracking but does not instruct the agent to warn the user that this personal data will be transmitted to a third-party merchant workflow. That creates a privacy and consent gap, especially because checkout involves external services and the email is not strictly required for core functionality.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.