Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Competitor Price Monitor
v1.0.0Automatically track competitor prices, product updates, and features, sending alerts and weekly reports to benchmark your market positioning.
⭐ 0· 202·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The described capability (monitoring competitor pages, change detection, weekly reports) matches the instructions to scrape and compare pages. However, the SKILL.md lists 'Brave Search API or web fetch capability' and alert channels (telegram/email) as requirements but the skill metadata declares no required environment variables or credentials. That mismatch (external APIs and alert channels implied but not declared) is a design inconsistency.
Instruction Scope
Instructions are high-level and permit broad agent behavior: discovery by search, site-wide scraping, storing baseline snapshots, and pushing alerts to external channels. They do not constrain which endpoints, which credentials, or where data is stored. Vague/open-ended guidance increases the chance the agent will use other available credentials or services on the host to implement alerts/storage.
Install Mechanism
This is an instruction-only skill with no install spec and no code files. That is the lowest-risk install profile — nothing is fetched or written by an installer.
Credentials
The SKILL.md implies needing access to external APIs (Brave Search) and delivery channels (telegram, email) but the manifest declares no required env vars or primary credential. That omission is concerning because an agent may attempt to use any available account tokens or secrets in the environment to perform those functions. There is no guidance to use dedicated, limited-scope credentials or to avoid exfiltrating sensitive data.
Persistence & Privilege
The skill is not marked 'always' and uses default autonomous invocation (allowed). Autonomous invocation is normal for skills, but combined with the instruction vagueness and unspecified credential requirements, it raises additional risk that the skill could act broadly without explicit user-per-action consent.
What to consider before installing
This skill appears to do what it says (scrape competitors and send alerts) but the runtime instructions are vague about how it will access search APIs, where it will store snapshots, and which accounts it will use to send alerts. Before installing: 1) Ask the author to declare required credentials and provide guidance to use dedicated, least-privilege API keys for search and delivery channels (e.g., a Telegram bot token or a dedicated SMTP/API key). 2) Require explicit configuration for storage (local path or a named cloud bucket) and confirm no other system credentials will be read. 3) Confirm the scraper respects robots.txt, rate limits, and legal/terms-of-service constraints. 4) If possible, run the skill in an isolated environment or with test/dummy credentials first. If the author cannot provide explicit env-var names, scopes, and storage endpoints, treat the skill as higher-risk and consider not installing it.Like a lobster shell, security has layers — review code before you run it.
latestvk97dxaxkxet312as9tw0qrfakh82vjg3
License
MIT-0
Free to use, modify, and redistribute. No attribution required.