Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

agent-shopping

Agent-powered smart shopping assistant

MIT-0 · Free to use, modify, and redistribute. No attribution required.
0 · 4 · 0 current installs · 0 all-time installs
MIT-0
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name and description match a shopping assistant; the SKILL.md describes product search, comparison, and eventual purchasing which aligns with the stated purpose. However the roadmap includes autonomous purchasing (v1.0) which raises expectations that credentials/payment methods will be required later even though none are declared now.
Instruction Scope
The runtime instructions are high-level and limited to parsing user intent and returning product recommendations/buy links. They do not instruct reading local files or secrets. However the doc instructs the operator to 'Set up API credentials in environment variables as needed for each supported platform' — this is vague and gives the agent open-ended authority to use unspecified credentials when integrating platform APIs.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk by the skill bundle itself, which is the lowest install risk.
!
Credentials
The registry lists no required environment variables, but the SKILL.md tells users to set API credentials in env vars as needed. That mismatch is concerning because it leaves unspecified which credentials the agent may later request (payment services, retailer APIs, account tokens). Requiring unspecified secrets is disproportionate without clearer justification.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. Autonomous invocation is allowed (platform default) but there are no indications the skill changes other skills or system-wide settings.
What to consider before installing
This skill is an instruction-only shopping assistant and currently has no declared required credentials, but its docs ask you to set API keys and its roadmap mentions autonomous purchasing. Before installing or using it: (1) ask the author for a precise list of required environment variables and exactly how they are used; (2) do not provide payment credentials or long-lived platform tokens until you verify the integration and scope; (3) require explicit confirmation from the agent/user before any purchase is initiated, and prefer short-lived or limited-scope API keys; (4) prefer using read-only API keys or affiliate links rather than account-level credentials; and (5) verify the skill's source/homepage and review any code before granting sensitive credentials.

Like a lobster shell, security has layers — review code before you run it.

Current versionv0.1.0
Download zip
latestvk97frvngvf2sn0jrd25sxrc6y983z3zc

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

🛒 Clawdis

SKILL.md

🛒 Agent Shopping

Agent-powered smart shopping assistant

What It Does

Search products, compare prices, and purchase items through AI agent conversations. Supports natural language queries like 'find me a USB-C cable under $10' and returns structured product recommendations with buy links.

Usage

When the user mentions buying, purchasing, shopping, or looking for product deals, this skill activates to help find the best options.

Example Prompts

  • "Find me the best deal on [product]"
  • "Compare prices for [product] across platforms"
  • "Is there a coupon for [product]?"
  • "Help me buy [product] under [budget]"

Configuration

Set up API credentials in environment variables as needed for each supported platform.

Architecture

User Request → Intent Parser → Product Search API → Result Ranker → Recommendation Display

Roadmap

  • v0.1: Basic product search via web search
  • v0.2: Platform API integration
  • v0.3: Price tracking and alerts
  • v1.0: Full autonomous purchasing flow

Author

Created by hanxueyuan as part of the Agent Commerce initiative. License: MIT

Files

1 total
Select a file
Select a file to preview.

Comments

Loading comments…