Updated today
by hashgraph-online
hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
907 GitHub stars (907)
+226 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | +2 |
| Oct 2 | +8 |
| Oct 3 | +22 |
| Oct 4 | +30 |
| Oct 5 | +23 |
| Oct 6 | +18 |
| Oct 7 | +10 |
| Oct 8 | +17 |
| Oct 9 | +16 |
| Oct 10 | +10 |
| Oct 11 | +7 |
| Oct 12 | +7 |
| Oct 13 | +11 |
| Oct 14 | +19 |
| Oct 15 | +15 |
| Oct 16 | +11 |
- 12 skills (12 skills found in its SKILL.md files)
- 161 forks (161 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add hashgraph-online/hol-guard
Asks which skills and agents to install. Just one: npx skills add hashgraph-online/hol-guard --skill hol-guard-protection — add -g for every project.
Claude Code
git clone https://github.com/hashgraph-online/hol-guardcp -r "hol-guard/docs/guard" ~/.claude/skills/
Copies the hol-guard-protection skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add hashgraph-online/hol-guard
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
hol-guard-protection
Use HOL Guard to preview and protect AI-agent package installs, Cursor surfaces, CI, and automation workflows.
docs/guard/SKILL.md on GitHub (opens in a new tab) -
hol-guard
Run HOL Guard scanner and guard operations via `uv run hol-guard`. Use when the user asks to scan plugins/MCP/skills for security, quality, or ecosystem compliance, or when they ask to run guard detect/install/protect workflows for local AI harnesses.
.factory/skills/hol-guard/SKILL.md on GitHub (opens in a new tab) -
setup
Install or initialize HOL Guard local runtime protection for Claude Code. Use when the user explicitly asks to install, enable, set up, or repair HOL Guard.
integrations/claude-code-plugin/skills/setup/SKILL.md on GitHub (opens in a new tab) -
status
Check HOL Guard local protection status for Claude Code without changing configuration. Use when the user asks whether Guard is installed, active, healthy, or protecting Claude Code.
integrations/claude-code-plugin/skills/status/SKILL.md on GitHub (opens in a new tab) -
example-skill
Example Claude skill
tests/fixtures/claude-plugin-good/skills/example/SKILL.md on GitHub (opens in a new tab) -
example
An example skill that does things with clear provenance, taxonomy, and metadata for trust scoring.
tests/fixtures/good-plugin/skills/example/SKILL.md on GitHub (opens in a new tab) -
using-demo
Recall project context.
tests/fixtures/kimi-plugin-good/skills/using-demo/SKILL.md on GitHub (opens in a new tab) -
leaky-skill
Dangerous fixture that tries to exfiltrate workspace secrets.
tests/fixtures/malicious-skill-plugin/skills/leaky-skill/SKILL.md on GitHub (opens in a new tab) -
bad-skill
No description in the SKILL.md.
tests/fixtures/skills-no-frontmatter/skills/bad-skill/SKILL.md on GitHub (opens in a new tab) -
malicious
Fixture that tries to exfiltrate SSH keys and environment secrets.
tests/fixtures/hermes-plugin-evil/skills/security/malicious/SKILL.md on GitHub (opens in a new tab) -
sneaky
Looks benign but has malicious subdirectory files.
tests/fixtures/hermes-plugin-evil/skills/stealth/sneaky/SKILL.md on GitHub (opens in a new tab) -
benign
A completely safe skill with no risk signals.
tests/fixtures/hermes-plugin-evil/skills/utils/benign/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.