SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-18 UTC

No new commits yet today

Open the update feed

Semiaberabuddies/Semia

Performs security auditing and static analysis on AI agent skills, identifying risky code and dangerous instructions bef…

No ratings yet Rate this skill
Stars612
Forks70
Watchers612
Open Issues3

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/berabuddies/Semia.git

OverviewOverview

Key Features

Performs security auditing and static analysis on AI agent skills, identifying risky code and dangerous instructions before a skill is installed or executed. Key capabilities include: 1. Skill static scanning: runs static analysis over skill directories and scripts to locate suspicious file access, network requests and command execution calls, producing a reviewable risk list; 2. Malicious instruction detection: checks skill descriptions and prompts for instructions that trick the agent into privilege escalation, secret leakage or bypassing security policies, blocking prompt-injection risks; 3. Supply-chain risk screening: verifies the origin and behavior of third-party skills before installation to reduce the chance of pulling in backdoors or malicious skills; 4. Multi-platform skill coverage: reviews skills targeting Claude Code, Codex, OpenClaw and similar agent runtimes, covering mainstream skill ecosystems.

Use Cases

Pre-install security review of AI agent skills, supply-chain risk screening of third-party skills, static scanning before publishing skill repositories for Claude Code/Codex/OpenClaw, detection of malicious instructions and privilege-escalation behavior.

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 ID1313
Data sourceGitHub
Repositoryberabuddies/Semia
CategoryAI & Agent Skills / Security & Compliance
Primary languagePython
LicenseApache License 2.0
Default branchmain
GitHub repository ID1229574762
Node IDR_kgDOSUnSag
Rank#1095 (position within the source ranking)
Site-wide popularity rank#1250 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006008002026-09-292026-10-112026-09-29 · 6082026-10-11 · 612
  • Now612
  • Previous point · 09-29 608
  • vs previous point +4
  • 2 data points 12 days
0204060802026-09-292026-10-112026-09-29 · 702026-10-11 · 70
  • Now70
  • Previous point · 09-29 70
  • vs previous point ±0
  • 2 data points 12 days

TimelineTimeline

Repository created2026-05-05 07:21:126 months ago
Data last updated2026-10-26 12:08:4923 days ago
Last commit2026-09-01 14:59:152 months ago

CommitLatest commit

Version [v0.1.3] committed by archidoge0. Update Category: Release & Version Milestone Deployment. Commit details: release: align v0.1.3 metadata. This update milestone release delivery and production build archiving.

379bc25 v0.1.3 archidoge0 2026-06-05

Next stepsNext steps