rhwp-security-sweep

rhwp-security-sweep is an Agent security & guardrails skill for AI agents, published by edwardkim in the rhwp repository on GitHub. Skillspace rates rhwp-security-sweep D (68/100) and it passed the safety scan; the rating is based on static analysis only.

HWP/HWPX 문서의 배포 전/수신 후 보안 점검을 수행합니다. inspect hidden-text(조판 은닉)·injection(프롬프트 주입 신호)·unicode(화면-바이트 불일치) 3축 스윕, edit redact --dry-run(읽기 전용 PII 탐지) → redact/sanitize 적용 → 재스윕 게이트까지 닫습니다. 트리거 — 사용자가 "이 문서 보내도 돼/배포 전 점검", "숨긴 텍스트/주입/유니코드 검사", "개인정보 마스킹하고 내보내", "받은 첨부 안전한지 확인", "메타데이터 지워줘", "rhwp inspect/redact/sanitize" 등을 요청할 때. gym 이 아니라 실사용 에이전트 경로다.

Grade
D
Quality
68 / 100
Safety
Passed
GitHub stars
3,807

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubedwardkim/rhwp

Our review

Architecture
88 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
Not declared. Check the repository before reusing it.

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Agent security & guardrails

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.