Works with the AI Agents you already use
Security Incident Triage
Suspected breach? Preserve evidence and scope impact before touching anything
$18
Security Incident Triage
Example session with this skill installed
We suspect an account compromise in our staging environment. Triage the incident using the supplied logs and authentication events. Preserve evidence, identify the likely scope and affected identities, and produce a containment plan. Do not modify systems or revoke credentials.
- Read your context and instructions
- Compiled the security incident triage
Incident Triage Record
INCIDENT SIGNAL
A synthetic staging user account shows an unusual successful sign in followed by access to an administrative route.
EVIDENCE AVAILABLE
- Authentication event log
- Application access log
- Synthetic user and role mapping
- Short configuration excerpt
- No endpoint telemetry
- No host forensic image
Initial Classification
Status: SUSPECTED COMPROMISE
The available evidence supports investigation but does not establish the complete attack path.
Timeline
T0
Normal activity for the affected test identity.
T1
Synthetic authentication log records a successful sign in from an unfamiliar source.
T2
The same identity reaches an administrative route not normally used by that account.
T3
No further activity is visible in the supplied evidence window.
Scope
Affected identity
One synthetic staging account.
Potentially affected systems
The application surface reachable by that identity.
Affected data
UNVERIFIED. The supplied logs do not establish whether protected data was read or modified.
Persistence
UNVERIFIED. No host, token issuance, or persistence evidence was supplied.
Lateral movement
NONE OBSERVED in the supplied evidence.
Evidence Gaps
- Session issuance and refresh history
- Identity provider audit trail
- Administrative action logs
- Host or container telemetry
- Data access audit events
Containment Priorities
- Preserve the current authentication and application logs.
- Preserve relevant session and identity audit records before expiration or rotation.
- Review active sessions associated with the affected test identity.
- Confirm whether the administrative route resulted in a protected action.
- Prepare credential and session containment for human approval if compromise is confirmed.
Current Verdict
The supplied synthetic evidence supports a suspected account compromise with limited observed scope.
Broader impact, persistence, and data exposure remain UNVERIFIED.
Handoff
Continue root cause investigation using preserved identity and application evidence. Route any confirmed vulnerability to the appropriate validation or remediation workflow.
No destructive containment or production changes are performed by this demo.
Connects securely to your tools. The creator never sees your data.
About this skill
Defensive incident triage for a suspected compromise. It preserves available evidence, scopes the likely entry point, identifies affected identities and data, assesses attacker capability and persistence, and produces a bounded containment and investigation plan before irreversible actions are taken.
What it does
- Preserves available evidence before containment actions can destroy useful context.
- Establishes the known incident timeline and separates observed facts from assumptions.
- Identifies likely entry points, affected identities, systems, data, and trust boundaries.
- Assesses signs of attacker capability, privilege, lateral movement, and persistence.
- Estimates the current blast radius using the evidence that is actually available.
- Produces prioritized containment actions with explicit tradeoffs and evidence preservation requirements.
- Routes confirmed vulnerabilities or root cause work to the appropriate specialist workflow.
How it works
- Intake captures the incident signal, affected environment, known timestamps, available evidence, and current operational state.
- Evidence preservation identifies logs, artifacts, sessions, configuration, and volatile information that should be retained before changes are made.
- Scope analysis maps observed indicators to identities, systems, data, and time windows.
- Impact assessment distinguishes confirmed effects from plausible but unverified exposure.
- Containment planning recommends the smallest actions needed to reduce risk while preserving investigation value.
- Handoff records unresolved questions and routes follow up work to root cause, vulnerability validation, remediation, or recovery workflows.
Boundaries
This skill is for defensive incident triage after a compromise is suspected.
It does not perform a penetration test, actively exploit systems to prove additional impact, implement remediation, or authorize production wide containment actions by itself.
A single suspected vulnerability that requires exploitability proof belongs to exploit-validation. Breadth focused vulnerability discovery belongs to vulnerability-assessment. Security fixes belong to security-fix-implementer.
Why this beats prompting it yourself
Generic incident response prompts often jump directly to remediation, rotate credentials too early, destroy useful evidence, or treat suspicions as confirmed facts. This skill prioritizes evidence preservation, separates observation from inference, scopes the incident before expanding action, and produces a containment plan that can be reviewed before execution.
Validation
This skill is part of the JetFerrari Security Engineering stack, which passed pack level routing integrity and native skill discovery validation. No per-skill runtime claim is asserted here beyond the evidence available for the stack.
Use cases
- Triage a suspected account or application compromise.
- Scope which identities, systems, and data may be affected.
- Preserve evidence before containment or remediation begins.
- Build an initial incident timeline from logs and supplied artifacts.
- Prioritize containment actions without destroying investigation value.
Known limitations
The quality of the triage depends on the evidence and incident context available to the agent. Missing logs, telemetry, identity history, or runtime access remain explicit evidence gaps. The skill does not independently authorize destructive containment, production wide shutdowns, credential revocation, or remediation changes.
Part of JetFerrari Security Engineering.
The quality of triage depends on the evidence, telemetry, logs, identities, systems, and incident context available to the agent. The workflow is designed to preserve evidence, scope impact, and plan containment rather than perform unrestricted destructive response actions. Missing telemetry can leave entry point, persistence, affected assets, or root cause unresolved until additional evidence becomes available.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago
Permissions
Access is limited to incident evidence and project context supplied for the current triage. The skill may inspect logs, configuration, source files, and other provided artifacts. It does not modify project files, revoke credentials, change production systems, perform destructive containment, harvest environment variables, or access external services by default.