Security audit
Incident Postmortem
Security checks for vulnerabilities and agentic risk
Overview
This skill is a structured guide for writing blameless incident postmortems and does not include code, persistence, external execution, or hidden data movement.
Safe to install for guided postmortem drafting. Users should still avoid pasting credentials, customer PII, tokens, raw IP addresses, or confidential incident details that do not need to appear in the final document.
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.