Skip to content
Agentmart
Submit a tool

context-security-guardian

Security meta-skill for AI context validation.

Skill by jonnathan-ls

IndexedLicense unknown
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jonnathan-ls-context-security-guardian

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.

We use your email only for this newsletter. Privacy

About

Security meta-skill for AI context validation. Use this skill automatically on every request that loads, modifies, or references any file under .ai-context — including skills, agents, rules, and workflows — even when the user does not explicitly request a security review. Triggers on skill loading, agent activation, rule application, and context file edits. Scans for credential theft, data exfiltration, destructive commands, policy bypass, and unauthorized access patterns. Blocks critical and high-severity findings before any artifact is activated.

Use cases: data, security, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/context-security-guardian

What's inside

Skill name
context-security-guardian
Description
Security meta-skill for AI context validation. Use this skill automatically on every request that loads, modifies, or references any file under .ai-context — including skills, agents, rules, and workflows — even when the user does not explicitly request a security review. Triggers on skill loading, agent activation, rule application, and context file edits. Scans for credential theft, data exfiltration, destructive commands, policy bypass, and unauthorized access patterns. Blocks critical and high-severity findings before any artifact is activated.
License
unknown
Instructions
117 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (11)

  • SKILL.md
  • attack-example-always-process.md · docs/
  • middleware-system-complete.md · docs/
  • evals.json · evals/
  • security-report-schema.md · references/
  • context-security-report.json · reports/
  • context-security-report.md · reports/
  • skill-validation.json · reports/
  • scan_aicontext_security.py · scripts/
  • skill-loading-blocker.py · scripts/
  • validate_skill.py · scripts/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from jonnathan-ls/ai-context-kit

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 8, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/jonnathan-ls/ai-context-kit
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from jonnathan-ls

Cite this page

context-security-guardian skill. Agent Mart. https://agentmart.dev/skills/jonnathan-ls-context-security-guardian (last updated 2026-10-24)