agentleFS
Sign inStart free
Hack23Hack23/European-Parliament-MCP-Server/.github/skills/incident-response/SKILL.md

incident-response

Skill30 starsChanged 9 months agoApache-2.0View on GitHub

Security incident detection, analysis, containment, and recovery per NIST SP 800-61r2 and ISO 27035

  • Installs packages

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 61 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify fix with security tests

    line 58
  2. Distinctive:

    Verify no unauthorized access occurred

    line 63
  3. Distinctive:

    Use GitHub Security Advisories for coordinated disclosure

    line 76
  4. Distinctive:

    Follow responsible disclosure timeline in SECURITY.md

    line 77

“Common” is measured: kept by at least 6 in 10 of the 61 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Incident Response Skill

Purpose

Establish procedures for detecting, analyzing, containing, and recovering from security incidents affecting MCP server projects.

When to Use

  • ✅ Responding to security vulnerability reports
  • ✅ Handling dependency compromise alerts
  • ✅ Managing secret exposure incidents
  • ✅ Addressing CodeQL critical findings
  • ✅ Processing SECURITY.md vulnerability disclosures

Incident Classification

SeverityExamplesResponse Time
🔴 CriticalSecret exposure, RCE vulnerability4 hours
🟠 HighAuthentication bypass, data exposure24 hours
🟡 MediumXSS, CSRF, moderate vulnerability72 hours
🟢 LowInformation disclosure, minor issues1 week

Response Workflow

1. Detection & Triage

  • GitHub Security Advisories notification
  • Dependabot critical alert
  • Security researcher disclosure via SECURITY.md
  • CodeQL/SAST finding in CI

2. Containment

# If secret exposed
# 1. Rotate immediately
# 2. Revoke old credentials
# 3. Review access logs

# If vulnerable dependency
npm audit fix
# or pin to safe version
npm install package@safe-version

3. Eradication

  • Apply security patch
  • Update vulnerable dependencies
  • Fix code vulnerability
  • Verify fix with security tests

4. Recovery

  • Deploy fixed version
  • Verify no unauthorized access occurred
  • Monitor for residual effects
  • Update security documentation

5. Lessons Learned

  • Document incident timeline
  • Update detection mechanisms
  • Improve prevention controls
  • Share findings with team

Communication

  • Use GitHub Security Advisories for coordinated disclosure
  • Follow responsible disclosure timeline in SECURITY.md
  • Notify affected users if personal data involved (GDPR)

ISMS Policy References

Core policies:

  • Incident Response Plan — Primary policy: NIST SP 800-61r2 lifecycle (Prep → Detection → Analysis → Containment → Eradication → Recovery → Lessons Learned)
  • Information Security Policy — Governance, transparency, stakeholder communication
  • Privacy Policy — GDPR Art. 33/34 breach notification (≤ 72 h to DPA)

Supporting policies:

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free