Afrexai Prospect Researcher Temp
v1.0.0Research and qualify B2B prospects using web search. Builds structured profiles with company intel, key contacts, pain points, and engagement recommendations.
⭐ 0· 75·0 current·0 all-time
by@ker2xu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The name/description (build B2B prospect profiles from public web search) matches the requested footprint: no binaries, no env vars, no installs. Everything required to perform the stated task is proportional. Note: the registry ownerId in the provided metadata (kn74m32v...) does not match the ownerId in _meta.json (kn76xhd...), which is an inconsistency in packaging/metadata to verify with the publisher.
Instruction Scope
SKILL.md clearly instructs only public web searches, cites sources, forbids scraping behind logins, and requires output to the included research-template.md. It does not instruct the agent to access unrelated local files, secrets, or external endpoints other than an explicit context-pack URL (https://afrexai-cto.github.io/context-packs).
Install Mechanism
No install spec or code files — instruction-only. There is nothing downloaded or written to disk by the skill bundle itself.
Credentials
The skill requests no environment variables, no credentials, and no config paths. This is proportionate to a public-web research task.
Persistence & Privilege
always:false and default model-invocation settings are used. The skill does not request permanent presence or elevated privileges.
Scan Findings in Context
[no-findings] expected: The package is instruction-only with no code files, so the regex-based scanner had nothing to analyze. This is expected for a pure-SKILL.md skill.
Assessment
This skill appears coherent and low-risk because it only instructs the agent to use public web search and fill a provided template, and it does not request credentials or install code. Before installing, verify the small metadata mismatch (ownerId) with the publisher if provenance matters; confirm your OpenClaw agent has a safe web-search provider configured (the skill needs search access to work); be aware the agent will surface publicly available personal data (names and LinkedIn URLs) — ensure this use complies with your privacy policies and applicable laws; review the external link (https://afrexai-cto.github.io/context-packs) if you don't want the agent to fetch third-party context packs; and consider limiting autonomous invocation if you prefer to review outputs manually.Like a lobster shell, security has layers — review code before you run it.
latestvk97312z6nazxx41srfmve60vh983thmw
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
