Search for, research, and verify non-tech founders on LinkedIn to identify high-value prospects for technology services (Web Dev, ERP, CRM, App Dev, SEO, AI). Generates professional PDF reports. Use when asked to find potential clients or leads.
Security Analysis
medium confidenceThe skill's files and runtime instructions are generally consistent with a LinkedIn lead‑generation workflow, but there are minor implementation gaps and practical caveats (PDF generation, LinkedIn authentication, small script bug) you should be aware of before using it.
Name and description match the instructions and bundled script: the SKILL.md describes searching LinkedIn, researching websites, doing gap analysis, and producing a prospect report. The included Python script produces an HTML report from JSON prospect data, which aligns with 'report generation' — however the skill claims to 'generate professional PDF reports' but provides no PDF conversion step or tool (e.g., wkhtmltopdf, headless Chrome print-to-pdf). Also LinkedIn access often requires authentication but the skill does not request credentials; it appears to assume the agent's browser tool has access.
The SKILL.md directs the agent to use browser and web_fetch to view LinkedIn profiles and company websites and to produce a report — these actions are within the stated purpose. The instructions do not ask the agent to read unrelated local files or environment variables, nor do they forward data to unknown external endpoints. Note: scraping/profile inspection may implicate LinkedIn terms of service and privacy considerations.
No install spec is included (instruction-only), so nothing is downloaded or written during install. The only code file is a small Python script that builds HTML from JSON; it does not perform network I/O or introduce hidden endpoints. The absence of a PDF converter is an implementation gap, not an installation risk.
The skill requests no environment variables or credentials, which is proportionate for the provided files. Practical caveat: performing LinkedIn searches and viewing 2nd-degree profiles may require an authenticated browser session; the skill does not declare or request LinkedIn credentials, so it relies on the agent environment to already have access. No unrelated secrets are requested.
The skill does not request permanent inclusion (always: false) and has no install actions that modify other skills or system-wide settings. It does not request elevated or persistent privileges.
Guidance
This skill appears to do what it says, but note three practical issues before installing: (1) The bundled script only generates HTML from JSON — there is no PDF conversion step included, so you’ll need a PDF renderer or a platform 'write/print' capability to produce PDFs. (2) The Python script has a minor bug: it only runs the generator when len(sys.argv) > 1 but then reads from stdin; this looks like a CLI logic error and may require fixing. (3) The workflow assumes the agent's browser/web_fetch can access LinkedIn profiles (often requiring login) — the skill does not request or store LinkedIn credentials, and scraping LinkedIn may violate their terms and raise privacy/consent concerns. If you plan to use this on real user data, confirm you have lawful access and consider adding an explicit, proportional authentication mechanism and a PDF generation step, or fix the script’s CLI logic.
Latest Release
v1.0.0
Initial release of linkedin-lead-gen. - Provides a structured workflow to identify and verify non-tech founders as high-value prospects on LinkedIn. - Outlines step-by-step process for target selection, strict filtering, deep research, and gap analysis. - Includes criteria for filtering out tech founders and those with strong internal tech teams. - Specifies tools to use (browser, web_fetch, write) for LinkedIn searches, website analysis, and PDF generation. - Details a professional, branded PDF report structure to present 10 qualified leads and tailored pitch ideas. - Highlights outreach principles focusing on personalization, problem-first approach, and local advantage.
More by @harshhmaniya
Published by @harshhmaniya on ClawHub
