ai-incident-response
Skill0 starsChanged 14 days agoMITView on GitHub
Respond to AI/LLM security incidents — successful prompt injection or jailbreak with impact, data leakage through a model or RAG, agent misuse of tools, compromised model artifacts or API keys, abuse of AI endpoints (cost/resource attacks) — including evidence collection of prompts and tool calls, containment and model/prompt rollback. Use when an AI feature caused or enabled a security incident.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- ahmedibm9-cyber/VibeGuardtheir own version, first seen Oct 20, 2026
- kumaran-is/claude-code-onboardingtheir own version, first seen May 25, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- kumaran-is/claude-code-onboarding★ 35same name
- ahmedibm9-cyber/VibeGuard★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository273 other files it gives its agents.
- ad-attack-path-analysisSkill
- adcs-security-reviewSkill
- ad-privileged-access-reviewSkill
- dcsync-detectionSkill
- gpo-security-reviewSkill
- kerberos-attack-detectionSkill
- agent-tool-permission-reviewSkill
- llm-gateway-controlsSkill
- llm-security-evaluationSkill
- mcp-server-security-reviewSkill
- model-artifact-securitySkill
- prompt-injection-reviewSkill
- rag-security-reviewSkill
- api-abuse-detectionSkill
- api-authorization-testingSkill
- api-inventorySkill
- api-schema-securitySkill
- dast-baselineSkill
- sast-triageSkill
- sca-dependency-riskSkill
- secure-code-reviewSkill
- security-requirementsSkill
- threat-modelingSkill
- asset-criticality-tieringSkill
- asset-inventory-reconciliationSkill
- external-attack-surface-reviewSkill
- shadow-it-discoverySkill
- aws-credential-compromiseSkill
- aws-iam-reviewSkill
- aws-org-guardrailsSkill
- cloudtrail-investigationSkill
- guardduty-triageSkill
- s3-exposure-reviewSkill
- azure-activity-investigationSkill
- azure-rbac-reviewSkill
- conditional-access-reviewSkill
- entra-audit-investigationSkill
- entra-signin-investigationSkill
- backup-assuranceSkill
- critical-service-mappingSkill
- ransomware-recoverySkill
- recovery-exerciseSkill
- cloud-exposure-reviewSkill
- cloud-incident-responseSkill
- cloud-logging-baselineSkill
- cloud-posture-assessmentSkill
- audit-evidence-packageSkill
- continuous-control-monitoringSkill
- control-mappingSkill
- control-testing-samplingSkill
- container-incidentSkill
- dockerfile-hardeningSkill
- image-scanningSkill
- runtime-detection-falcoSkill
- db-audit-loggingSkill
- db-exfiltration-investigationSkill
- db-hardeningSkill
- db-privilege-reviewSkill
- data-classificationSkill
- data-discoverySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 31
Remove poisoned content from indexes.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Incident Response
Incident types
| Type | Examples |
| Injection with impact | Assistant exfiltrated email contents via rendered link; agent executed attacker-supplied command |
| Data leakage | RAG answered with documents the user shouldn't access; model output reproduced another tenant's data |
| Credential/key abuse | Stolen LLM provider API keys used for resale ("LLMjacking"), cloud AI service abuse |
| Model supply chain | Malicious model file executed code on a data scientist workstation or inference server |
| Resource abuse | Unbounded consumption driving cost or outage |
| Harmful output | Policy-violating content delivered to customers |
Evidence to collect
Prompt and conversation logs (system prompt version, user inputs, retrieved chunks with document IDs, tool calls with parameters and results, model/version, temperature), gateway logs (llm-gateway-controls), application logs, provider usage logs/billing, identity of the user/session, the triggering content (malicious document/web page/email) preserved as evidence.
Containment options
- Disable the affected tool/connector or the feature (feature flag/kill switch).
- Remove poisoned content from indexes; re-index.
- Roll back prompt/model/guardrail version.
- Rotate exposed API keys; set provider spend limits; block abusive accounts.
- For malicious model artifacts: treat host as compromised (
linux-incident-triage), rotate credentials on it.
Analysis
Reconstruct the chain: content source → retrieval/ingestion → model behaviour → action/output → impact. Determine all users exposed to the same poisoned content or feature behaviour (query logs for the document ID or tool pattern). Feed new test cases into llm-security-evaluation regression suites.
Reporting
Map to OWASP LLM Top 10 and MITRE ATLAS techniques; assess privacy notification (privacy-incident-assessment); consider AI-specific regulatory duties (e.g., EU AI Act serious-incident reporting for high-risk systems, where applicable).
Related skills
prompt-injection-review, llm-gateway-controls, model-artifact-security, incident-command
References
- MITRE ATLAS (case studies & techniques): https://atlas.mitre.org/
- OWASP GenAI Incident Response Guide: https://genai.owasp.org/resource/genai-incident-response-guide-1-0/
- NIST AI 600-1 Generative AI Profile: https://www.nist.gov/publications/artificial-intelligence-risk-management-framework-generative-artificial-intelligence
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
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.