More screenshots
Works with the AI Agents you already use
OSINT: Investigations as Evidence Chains
Run open-source intelligence as an evidence chain — scope first, grade every source, pivot only on confirmed identifiers, log as you go, and report the gaps honestly.
$5
OSINT: Investigations as Evidence Chains
Example session with this skill installed
A phishing-adjacent domain is impersonating us. Identify who operates it using only public data, with every claim sourced and graded.
- Read your context and instructions
- Compiled the osint
Scope written before any tool opened: 'Identify the operator of secure-docs-verify, public data only, no contact.' The deliverable was fixed in advance — a report with findings, timeline, entity graph, and gaps — because the deliverable shapes what gets collected. DNS plus certificate transparency: the certificate was issued 3 days before the first phishing report, and 4 other domains share the same certificate — pivot candidates, not conclusions. Hosting: all five domains sit on the same budget VPS provider on adjacent IPs — an infrastructure link, grade B. One sibling domain has a leftover development subdomain exposing a login page; entering no credentials, the reset form's autocomplete suggests an m.okafor address — publicly rendered by the site itself, fair game, no intrusion. Pivot on the email, one hop, one verification: breach-compilation mentions tie it to a freelance web developer profile with a portfolio — including, ironically, a testimonial from a 'document verification service.' Corroborated by a second source before pivoting again. Report: operator identified with medium-high confidence, every hop sourced and graded, the email-to-person link marked as the weakest hop (single-source corroboration), and a gaps section noting no direct infrastructure-to-identity proof. Honest confidence beats false certainty.
Connects securely to your tools. The creator never sees your data.
About this skill
OSINT fails two ways: collecting everything and concluding nothing, or concluding everything from one screenshot. The discipline is the evidence chain — every claim linked to a captured source, every pivot justified by a confirmed identifier, every gap labeled as a gap. This skill covers scoping before collecting, grading sources A through D, pivoting one confirmed identifier at a time with corroboration, the four investigation shapes (infrastructure, person, incident, corporate), logging as you go, and a report structure that includes a gaps section — because a report without one is overselling. Public data only, no deception, no intrusion.
Attribution is the last step and the weakest claim — it gets graded accordingly, never stated as fact from a single hop.
A grade-C lead is a lead, never a conclusion; only corroboration turns coincidence into connection.
Public data has gaps that stay gaps. A report without a gaps section is overselling.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 days ago
Permissions
No special permissions declared or detected