Startup Info
v1.0.0Generate concise investor-style briefings on startups using live web searches to extract verified company info, funding, founders, traction, and competitors.
⭐ 1· 310·0 current·0 all-time
byBruno Pérez@brunobuddy
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (investor-style briefings) align with the instructions: the SKILL.md explicitly instructs the agent to perform web searches, fetch company home/about pages, and extract funding/founder/traction/competitor data. The skill declares no binaries, env vars, or installs—nothing extraneous is requested for the stated task.
Instruction Scope
Runtime instructions are narrowly scoped to web searches, limited follow-up searches (no more than 2 rounds), page fetching, and producing a fixed briefing template. The prompt does not ask the agent to read local files, environment variables, or other system state. One minor operational note: it permits using search snippets when sites block fetching (expected for blocked pages like LinkedIn/Crunchbase).
Install Mechanism
There is no install spec and no code files—this is instruction-only. That minimizes disk writes and executable installs and is proportionate to the described functionality.
Credentials
The skill requests no environment variables, credentials, or config paths. It relies on the agent's web-search/browsing capability (which may itself be backed by provider-specific API keys), but the skill does not request unrelated secrets or elevated access.
Persistence & Privilege
always:false (not force-included). disable-model-invocation:false (normal—agent may invoke it autonomously). The skill does not request persistent system-wide changes or access to other skills' configs.
Assessment
This skill is coherent and low-risk in itself, but before enabling it: confirm which browsing/search provider the agent will use and what that provider can access (browser tool may have its own API keys or web access policies); expect some blocked pages (LinkedIn, Crunchbase) and verify sources cited in the output since the prompt allows relying on snippets; if you plan to research private or sensitive startups, be aware of legal/terms-of-service constraints for scraping certain sites.Like a lobster shell, security has layers — review code before you run it.
latestvk973mdea08tchmtkae7qcg97gs821ywc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.