SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

secureclawadversa-ai/secureclaw

Provides security auditing, hardening, and integrity verification for OpenClaw agent skills to prevent tampering and LLM…

No ratings yet Rate this skill
Stars347
Forks46
Watchers347
Open Issues7

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/adversa-ai/secureclaw.git

OverviewOverview

Key Features

Provides security auditing, hardening, and integrity verification for OpenClaw agent skills to prevent tampering and LLM security risks. Key capabilities include: 1. Skill Audit: quick-audit.sh scans skill directories and matches dangerous patterns against 4 JSON pattern databases to output a risk list; 2. Skill Hardening: quick-harden.sh automatically applies permission tightening and rule constraints to high-risk skills, reducing abuse risk; 3. Integrity Verification: scan-skills.sh compares skill file hashes to detect tampered or replaced skills; 4. Behavioral Rule Injection: SKILL.md embeds 15 behavioral rules that constrain agent behavior at skill load time and block unauthorized operations.

Use Cases

Pre-release security audit of OpenClaw agent skills, skill file integrity verification, hardening of high-risk skills, OWASP LLM Top 10 risk assessment, agent behavioral rule enforcement.

Target Roles

AI / Algorithm Engineer, Network & System Security Engineer, DevOps / Operations Engineer, Test / QA Engineer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID2183
Data sourceGitHub
Repositoryadversa-ai/secureclaw
CategoryAI & Agent Skills / AI Security & Compliance
Primary languageTypeScript
LicenseNot specified
Default branchmain
GitHub repository ID1154405739
Node IDR_kgDORM7Vaw
Rank#1696 (position within the source ranking)
Site-wide popularity rank#1901 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

01002003004002026-09-242026-10-112026-09-24 · 3482026-10-11 · 347
  • Now347
  • Previous point · 09-24 348
  • vs previous point -1
  • 2 data points 17 days
02040602026-09-242026-10-112026-09-24 · 462026-10-11 · 46
  • Now46
  • Previous point · 09-24 46
  • vs previous point ±0
  • 2 data points 17 days

TimelineTimeline

Repository created2026-02-10 10:55:409 months ago
Data last updated2026-10-26 12:21:0321 days ago
Last commit2026-04-12 16:40:467 months ago

CommitLatest commit

Version [2.1.0] committed by adversa-ai. Update Category: Documentation & Guidelines Update. Commit details: Merge pull request #7 from dasha-512/docs/align-doc-check-count. This update improves usage instructions, deployment guides, and developer docs.

bf17e2b v2.1.0 adversa-ai 2026-02-28