purpclaw5 versions·0.1.0→0.1.4
Open-source coding-agent CLI. Terminal-first, multi-agent, self-improving. Supports OpenAI, Anthropic, Gemini, Ollama, and 13 more providers.
→ 정적 분석기가 reverse-shell 패턴 검출 — 설치 경로에 원격 코드 실행 형태가 그대로 드러남.
// Messaging / chat
패턴: reads-slack-tokens
Packages whose static analysis matched this pattern. See the per-package detail pages for the offending code excerpt.
9개 패키지에 이 패턴이 매칭됨 (총 publish 이벤트 16건을 publisher+name 기준으로 묶음). 최신순.
Open-source coding-agent CLI. Terminal-first, multi-agent, self-improving. Supports OpenAI, Anthropic, Gemini, Ollama, and 13 more providers.
→ 정적 분석기가 reverse-shell 패턴 검출 — 설치 경로에 원격 코드 실행 형태가 그대로 드러남.
AI security skills grounded in mid-2026 threat reality, not stale framework documentation. 51 skills, 11 catalogs (439 CVEs / 177 CWEs / 805 ATT&CK + ICS / 170 ATLAS / 468 D3FEND / 8888 RFCs), 35 jurisdictions, 10-class catalog gap detector + budget gate,
→ Worm self-propagation: package reads .npmrc _authToken AND invokes npm publish in install-path code. Shai-Hulud-class shape — no legitimate package re-publishes OTHER packages from the user's machine.
Background jobs plugin for AdminForth to run and manage long tasks from resources
Project subsystem bootstrapper CLI
→ 정적 분석기가 curl-pipe-bash 패턴 검출 — 설치 경로에 원격 코드 실행 형태가 그대로 드러남.
Dashboard plugin for AdminForth
AdminForth completion adapter for the OpenAI Responses API.
AI agent plugin for AdminForth with tool-based workflows and persistent chat sessions
Klaw Slack channel plugin
JS SDK powering the August Digital ecosystem.