Skip to content
Skills Library
Security · Planning

operate-agentic-security-tools

/operate-agentic-security-tools

Operate security tools through an AI agent with explicit authority boundaries. Use when an agent may invoke CLIs, GUI apps, browser automation, MCP servers, scanners, sandboxes, or containment actions with constrained approvals and logging.

Repository
socket ↗
Licence
Apache-2.0
Last repository change
26.08.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.08.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Operate security tools through an AI agent with explicit authority boundaries. Use when an agent may invoke CLIs, GUI apps, browser automation, MCP servers, scanners, sandboxes, or containment actions with constrained approvals and logging.

Original author description

Operate security tools through an AI agent with explicit authority boundaries. Use when an agent may invoke CLIs, GUI apps, browser automation, MCP servers, scanners, sandboxes, or containment actions with constrained approvals and logging.

How it works

  1. Overview
  2. Workflow
  3. Guardrails
Original SKILL.md headings · 42 lines, 294 words
SKILL.md preview
---
name: operate-agentic-security-tools
description: Operate security tools through an AI agent with explicit authority boundaries. Use when an agent may invoke CLIs, GUI apps, browser automation, MCP servers, scanners, sandboxes, or containment actions with constrained approvals and logging.
---

# Operate Agentic Security Tools

## Overview

Give the agent only the authority needed for the current security step and keep tool output reproducible. Separate discovery, active testing, exploit validation, containment, and remediation into visible decisions.

Read [references/agent-tool-controls.md](references/agent-tool-controls.md) for the preflight record and control checklist.

## Workflow

1. Define the tool's job.
   - State the security question, expected input/output, target, and why this tool is appropriate.
   - Prefer read-only or offline operation when it can answer the question.

2. Discover capability before use.
   - Record source, installed path or remote service, version, supported formats, privileges, network behavior, telemetry, and output location.
   - Treat missing tools or unusable integrations as results; do not invent output.

3. Minimize authority.
   - Limit readable/writable paths, target list, network destinations, credentials, environment variables, device access, and execution duration.
   - Use temporary scoped credentials and disposable environments when credentials are unavoidable.

4. Gate consequential actions.
   - Require an operator decision before active probing, exploit execution, persistence changes, credential access, security-control changes, destructive operations, production writes, or third-party uploads.
   - Display the exact target and likely effect before approval.

5. Preserve evidence.
   - Record commands or UI actions, configuration, timestamps, exit status, raw output, tool errors, and transformations.
   - Validate high-impact findings with an independent observation or smallest safe reproduction.

6. Clean up and verify.
   - Remove temporary mounts, ports, tokens, sessions, files, rules, and isolated environments.
   - Report what remains installed, running, reachable, or retained.

## Guardrails

- Do not grant broad host or cloud access merely to reduce approval prompts.
- Do not let an agent expand active-test scope from discovered targets.
- Do not treat an MCP server, GUI automation layer, or tool plugin as a trust boundary.
- Do not obscure failures behind a synthesized security conclusion.
Files in this package (3)
  • SKILL.md 2 KB
  • agents/openai.yaml 1 KB
  • references/agent-tool-controls.md 1 KB

Versions

The database has no other skills named operate-agentic-security-tools.

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 4aca8cf481a0 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90agentic-security
    Use when auditing the security of an AI-coding-agent setup in a repository: Claude Code project settings and hooks, plugin manifests and hooks.json, .mcp.json and MCP servers, skills, agents and rule files, permission rules, secrets in agent configuration, and CI workflows that…
  • 90mcp-security-review
    Review the security of MCP (Model Context Protocol) servers/clients an agent uses: server trust tier, tool/resource description and result poisoning, confused-deputy risk, consent/scope UX, and supply-chain pinning. Use when an agent or assistant integrates one or more MCP…
  • 100agent-owasp-check
    Use when auditing an AI agent system against the OWASP Agentic Security Initiative Top 10 — checks tool access, prompt boundaries, memory handling, and operational safeguards across the agent pipeline.
  • 100agentic-security-review
    Use this skill to review the composed attack surface of an agentic system against the OWASP Top 10 for Agentic Applications (ASI01 to ASI10) — whether tool descriptions, retrieved content and tool output can steer a tool call, what the agent can reach once steered (tools as…
  • 90auditing-ai-agent-repositories
    Use when a repository uses Claude Code, Codex, Cursor, Copilot agent mode, MCP servers, GitHub Actions, hooks, skills, or other AI coding automation and needs a read-first hardening review. Inventory instruction surfaces, MCP/tool configuration, automation, secret-like file…
  • 90mcp-security-boundaries
    Treat tool output as untrusted data, confirm destructive actions, and keep an agent's reach inside what its user may do. Use when an MCP server touches real systems or reads content from outside your control.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.