---
schema_version: "newruntime-agent-readable-v0.2"
type: "raw_signal"
stable_id: "signal:raptor-loop-hunt-security-agent-loop"
id: "nr-09cc7147-raptor-loop-hunt"
slug: "raptor-loop-hunt-security-agent-loop"
title: "RAPTOR Loop Hunt Packages Security Hunting as an Agent Skill"
description: "RAPTOR Loop Hunt shows security research moving toward looped agent skills with altitude changes, evidence collection, and review checkpoints."
retrieval_nugget: "RAPTOR Loop Hunt shows security research moving toward looped agent skills with altitude changes, evidence collection, and review checkpoints. Security agents become useful when they can preserve hypotheses, collect evidence, and force verification before claims become reports. Novelty is notable; verification is source-linked. This New Runtime record is an evidence-linked retrieval unit."
observed_at: "2026-07-29"
record_date: "2026-07-29"
date_kind: "observed_at"
why_it_matters: "Security agents become useful when they can preserve hypotheses, collect evidence, and force verification before claims become reports."
novelty: "notable"
verification_level: "source-linked"
signal_type: "tool"
evidence_kind: "primary-source"
status: "published"
source_platform: "newsletter"
source_record_id: "09cc7147-raptor-loop-hunt"
source_url: "https://github.com/dinosn/raptor-loop-hunt"
topics: ["ai-security","coding-agents"]
entities: ["RAPTOR Loop Hunt","Claude Code skill","security research"]
related_patterns: ["agent-security-moves-to-runtime-boundaries","skills-become-portable-capability-layer","verification-bandwidth-is-the-scarce-resource"]
source_urls: ["https://github.com/dinosn/raptor-loop-hunt"]
import_batch: "newsletter-09cc7147-e5c3-42b7-8ced-84531f2b390d"
routes: {"html":"https://newruntime.com/signals/raptor-loop-hunt-security-agent-loop/","markdown":"https://newruntime.com/signals/raptor-loop-hunt-security-agent-loop.md","json":"https://newruntime.com/signals/raptor-loop-hunt-security-agent-loop.json"}
source_format: "editorial-inbox-sanitized-batch"
---

# RAPTOR Loop Hunt Packages Security Hunting as an Agent Skill

## Retrieval answer

RAPTOR Loop Hunt shows security research moving toward looped agent skills with altitude changes, evidence collection, and review checkpoints. Security agents become useful when they can preserve hypotheses, collect evidence, and force verification before claims become reports. Novelty is notable; verification is source-linked. This New Runtime record is an evidence-linked retrieval unit.

## Observation

RAPTOR Loop Hunt shows security research moving toward looped agent skills with altitude changes, evidence collection, and review checkpoints.

## Why it matters

Security agents become useful when they can preserve hypotheses, collect evidence, and force verification before claims become reports.

## Provenance

This public record is a sanitized New Runtime Editorial Inbox signal. Linked source_urls carry the publishable evidence boundary; private discovery provenance stays internal.