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

No new commits yet today

Open the update feed

agentguardGoPlusSecurity/agentguard

Provides security review and trust management for AI agent skills and plugins, blocking malicious skills,…

No ratings yet Rate this skill
Stars467
Forks66
Watchers467
Open Issues15

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/GoPlusSecurity/agentguard.git

OverviewOverview

Key Features

Provides security review and trust management for AI agent skills and plugins, blocking malicious skills, prompt injection, and unverified code before they enter the execution environment. Key capabilities include: 1. Malicious skill detection: scans skill packages for hidden backdoors, credential theft, and data exfiltration behavior to prevent dangerous skills from loading; 2. Prompt injection identification: detects prompt injection content in skill descriptions or instructions that attempts to hijack agent behavior, reducing manipulation risk; 3. Unverified code flagging: marks code of unknown or unaudited origin with risk flags to avoid direct execution; 4. Automatic scanning of new skills: triggers security scans automatically during skill installation or first load, eliminating manual checks; 5. Full scan of loaded plugins: runs a unified scan across all currently loaded plugins to surface existing risks; 6. Trust level determination: infers a skill's trust level from scan results and source information to assist release decisions; 7. Capability inference and tool mapping: analyzes the capabilities a skill can actually invoke and builds tool mapping relationships so the agent knows what each skill can do; 8. Trust registry registration: writes scan and assessment results into a trust registry to form traceable skill trust records.

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 ID1525
Data sourceGitHub
RepositoryGoPlusSecurity/agentguard
CategoryAI & Agent Skills / Agent Security & Trust Management
Primary languageTypeScript
LicenseMIT License
Default branchmain
GitHub repository ID1147844273
Node IDR_kgDORGq2sQ
Rank#1346 (position within the source ranking)
Site-wide popularity rank#1525 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006002026-09-292026-10-112026-09-29 · 4632026-10-11 · 467
  • Now467
  • Previous point · 09-29 463
  • vs previous point +4
  • 2 data points 12 days
0204060802026-09-292026-10-112026-09-29 · 672026-10-11 · 66
  • Now66
  • Previous point · 09-29 67
  • vs previous point -1
  • 2 data points 12 days

TimelineTimeline

Repository created2026-02-02 09:21:259 months ago
Data last updated2026-10-26 12:12:5022 days ago
Last commit2026-10-10 08:12:141 months ago

CommitLatest commit

Version [v1.2.1] committed by Mr-Lucky. Update Category: Bug Fixes & Stability Improvements. Commit details: version patch. This update resolves known runtime errors and enhances system reliability.

e378f26 v1.2.1 Mr-Lucky 2026-10-10