Back to skill
Skillv1.1.0

ClawScan security

Openclaw Skill · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 6, 2026, 10:04 AM
Verdict
Benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's declared purpose (finding/enriching business leads) matches its runtime instructions and required credential (EEF_API_KEY); it is an instruction-only integration that calls the Easy Email Finder API and does not request unrelated access.
Guidance
This skill is internally coherent, but before installing: (1) confirm you trust the Easy Email Finder service and review its privacy/terms (the skill will transmit queries and website URLs to that external API); (2) keep your EEF_API_KEY secret and scoped/rotated as appropriate; (3) be aware enrich calls consume paid credits and are rate-limited; and (4) verify the skill publisher/source since registry metadata shows no homepage while SKILL.md references easyemailfinder.com.

Review Dimensions

Purpose & Capability
okName/description promise (search/enrich businesses with emails, tech stack, social links) aligns with the single required credential (EEF_API_KEY) and the API endpoints documented in SKILL.md. There are no extra binaries, config paths, or unrelated credentials requested.
Instruction Scope
okSKILL.md is explicit about endpoints, request formats, authentication, rate limits, and credit costs. It only instructs the agent to call https://easyemailfinder.com API endpoints and to read the EEF_API_KEY env var; it does not instruct the agent to read other files, environment variables, or system paths.
Install Mechanism
okNo install spec and no code files — instruction-only. This minimizes on-disk risk; nothing is downloaded or executed by the skill itself.
Credentials
okOnly one environment variable is required (EEF_API_KEY) and it is the documented bearer token for the API. The credential request is proportionate to the skill's stated purpose and is declared as the primary credential.
Persistence & Privilege
okalways is false (default) and the skill makes no claims to modify agent/system settings. Autonomous invocation is allowed (platform default) but not combined with other privilege-escalating factors.