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

No new commits yet today

Open the update feed

hol-guardhashgraph-online/hol-guard

Provides security protection for AI coding assistants and agent runtime environments, blocking prompt injection,…

No ratings yet Rate this skill
Stars845
Forks149
Watchers845
Open Issues123

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/hashgraph-online/hol-guard.git

OverviewOverview

Key Features

Provides security protection for AI coding assistants and agent runtime environments, blocking prompt injection, secret leakage and malicious supply-chain risks when installing MCP servers, loading plugins and executing tool calls. Key capabilities include: 1. Online MCP server verification: verify --online checks the HTTP reachability and source trustworthiness of remote MCP servers, flagging unreachable or suspicious services before they are connected; 2. Runtime security scanning: detects prompt injection, credential leakage and dangerous instructions during agent sessions and tool calls, and blocks them on detection; 3. GitHub Actions integration: ships a ready-to-reference Action configuration that embeds security scanning into CI pipelines so checks run automatically before code merge; 4. Multi-client support: offers a unified protection entry point for mainstream agent clients such as Claude Code, Cursor, Gemini CLI and OpenCode.

Use Cases

Security review before installing third-party MCP servers or plugins in AI coding assistants, blocking prompt injection and secret leakage during agent runtime, running automated security scans in CI pipelines, and verifying supply-chain dependencies and plugin provenance.

Target Roles

Network & System Security Engineer, AI / Algorithm Engineer, DevOps / Operations Engineer, Full-stack / Indie Developer.

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 ID1266
Data sourceGitHub
Repositoryhashgraph-online/hol-guard
CategoryNetwork & System Security / AI Agent Security
Primary languagePython
LicenseApache License 2.0
Default branchmain
GitHub repository ID1194748811
Node IDR_kgDORzZriw
Rank#872 (position within the source ranking)
Site-wide popularity rank#983 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02505007501k2026-09-252026-10-112026-09-25 · 6682026-10-11 · 845
  • Now845
  • Previous point · 09-25 668
  • vs previous point +177
  • 2 data points 16 days
0501001502026-09-252026-10-112026-09-25 · 1012026-10-11 · 149
  • Now149
  • Previous point · 09-25 101
  • vs previous point +48
  • 2 data points 16 days

TimelineTimeline

Repository created2026-03-28 19:02:157 months ago
Data last updated2026-10-26 12:05:2123 days ago
Last commit2026-10-11 03:44:551 months ago

CommitLatest commit

Committed by zerocodefast. Update Category: New Features & Capability Expansion. Commit details: feat(guard): decide bulk approve-once eligibility in the native resident (#4020). This update introduces new capabilities and expands supported use cases.

52eb843 zerocodefast 2026-10-11

Next stepsNext steps