plugin-scanner
Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- plugin-scanner
- license
- Apache-2.0
- description
- Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them.
03 SKILL.md 正文
Plugin Scanner
Use HOL's local plugin-scanner when a user asks to inspect an AI agent skill, plugin, MCP server, agent package, or repository before installation or use.
The scanner is shipped by the open-source plugin-scanner Python distribution. It is built from the same HOL Guard source repository, but it is intentionally packaged separately from the hol-guard runtime CLI. Scanning runs locally and does not require Guard Cloud.
When to use this skill
Use this skill when the user asks to:
- scan or audit a
SKILL.mdbefore installing it; - inspect an MCP server or agent plugin for security risks;
- check a third-party agent repository before trusting it;
- look for prompt injection, credential exposure, unsafe commands, or suspicious package/install behavior;
- validate a skill/plugin repository in CI or before publishing it.
Safety rules
- Never execute code from the target repository just to scan it.
- Never run its install scripts, package lifecycle hooks, or arbitrary shell commands.
- Never read
.envfiles, credential stores, private keys, or unrelated user secrets. - Prefer scanning a local path or a repository the user has already chosen to inspect.
- Treat scanner findings as security evidence, not a guarantee that a package is safe.
- Ask before installing
plugin-scannerif the command is not already available.
Workflow
1. Check for the scanner
command -v plugin-scanner
If it is not installed, explain that plugin-scanner is a separate open-source CLI distribution from the HOL Guard repository and, with user approval, install it in an isolated CLI environment:
pipx install plugin-scanner
Do not assume an existing hol-guard installation also provides the plugin-scanner command. If pipx is unavailable, point the user to the plugin-scanner installation instructions rather than silently changing their Python environment.
2. Scan the target without executing it
For a repository or directory:
plugin-scanner scan PATH --format markdown
For machine-readable results:
plugin-scanner scan PATH --format json
For Agent Skill / plugin structure validation:
plugin-scanner lint PATH
plugin-scanner verify PATH
Use the narrowest target path that contains the material the user asked to inspect.
3. Interpret findings
Summarize:
- the target that was scanned;
- the highest severity finding;
- concrete files/rules involved;
- whether the scanner found prompt-injection, secret/exfiltration, command-execution, dependency/install, or MCP-specific risks;
- the recommended next action.
Do not claim "safe" solely because no finding was returned. Say that no covered issue was detected by the current scan.
Common prompts
- "Scan this skill before I install it."
- "Check this MCP server for prompt injection or suspicious commands."
- "Audit this agent plugin repository."
- "Verify this SKILL.md and tell me what is risky."
- "Run a security check on this AI tool before we add it to our project."
Source
- Plugin Scanner source: https://github.com/hashgraph-online/hol-guard
- Plugin Scanner package: https://pypi.org/project/plugin-scanner/
- Distribution companion: https://github.com/hashgraph-online/hol-guard-plugin
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.