Skillguard
Security scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts).
Connector by RudrenduPaul · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Skillguard?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/rudrendupaul-skillguard
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 1 read · 1 write · 0 delete
- Secrets
- None asked for
- Install scripts
- Not scanned yet
- Runs as
- Python package
Tools by what they do 2
Read from the source code; the running server may list different tools.
Read 1 · Look things up without changing anything.
scan_skill
Write 1 · Create, change, send or run things.
run
Files it touches
- Any path the agent passes to its tools
Tools (2)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
runDescription is built at runtime.
scan_skillScan a third-party agent skill for known attack patternsScans a third-party AI agent-skill directory (a SKILL.md manifest plus its hooks/scripts) for known attack patterns before it is installed or run: remote-code-execution hooks, declared-scope-vs-actual-behavior mismatches, file-scope escalation, supply-chain-risky install hooks, obfuscated payloads, and credential harvesting. Call this before installing or executing any agent skill that was not authored by you or your organization -- the same way you would not run an unreviewed shell script from a stranger. Returns a structured scan result (findings, severities, exit code) as JSON; a non-zero e…
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Weekly downloads
- 27
- Last commit
- Sep 25, 2026 (1 month ago)
- Last release
- Sep 25, 2026 (1 month ago)
- Last package publish
- Aug 11, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.RudrenduPaul/skillguard- Version
- 0.2.5
- Auth
- No auth
- Packages
- pypi skillguard-cli
- License
- Apache-2.0
- Repository
- github.com/RudrenduPaul/skillguard
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
More from RudrenduPaul
- 0.600score
Neuronscope
RudrenduPaul
Traces which neurons and attention heads drive a language model's output via MCP tools.
ConnectorAFreshness: ALocal★ 1↓ 45/wkClaude Code +5 - 0.594score
Evolveguard
RudrenduPaul
Wraps the evolveguard CLI as a single generic MCP tool for agent-skill file safety checks.
ConnectorAFreshness: ALocal★ 1↓ 36/wkClaude Code +5 - 0.593score
Agent Eval
RudrenduPaul
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
ConnectorAFreshness: ALocal↓ 63/wkClaude Code +5 - 0.593score
Agenticworkspace
RudrenduPaul
Wraps the AgenticWorkspace CLI as a single generic MCP tool for repo workspace scans.
ConnectorAFreshness: ALocal↓ 62/wkClaude Code +5 - 0.593score
Llmscout
RudrenduPaul
Zero-config SEO and GEO checker: 21 technical-SEO and generative-engine checks for a live site.
ConnectorAFreshness: ALocal↓ 61/wkClaude Code +5 - 0.592score
Agent Observability
RudrenduPaul
AI agent observability with deterministic record/replay for debugging agent failures.
ConnectorAFreshness: ALocal↓ 60/wkClaude Code +5
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Skillguard running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Skillguard MCP server. Agent Mart. https://agentmart.dev/connectors/rudrendupaul-skillguard (last updated 2026-10-24)