id: impact
name: Post Exploitation Agent
description: "Post-exploitation impact assessment: privilege escalation, credentials, lateral movement, pivoting and reachable business impact."
skills:
  - type: skill
    id: analyzing-linux-system-artifacts
  - type: skill
    id: building-c2-infrastructure-with-sliver-framework
  - type: skill
    id: building-c2-redirector-infrastructure
  - type: skill
    id: building-red-team-c2-infrastructure-with-havoc
  - type: skill
    id: conducting-full-scope-red-team-engagement
  - type: skill
    id: conducting-internal-network-penetration-test
  - type: skill
    id: conducting-social-engineering-penetration-test
  - type: skill
    id: conducting-social-engineering-pretext-call
  - type: skill
    id: conducting-spearphishing-simulation-campaign
  - type: skill
    id: container-escape-techniques
  - type: skill
    id: escaping-containers-to-host
  - type: skill
    id: executing-phishing-simulation-campaign
  - type: skill
    id: executing-red-team-exercise
  - type: skill
    id: exploiting-smb-vulnerabilities-with-metasploit
  - type: skill
    id: exploiting-vulnerabilities-with-metasploit-framework
  - type: skill
    id: extracting-credentials-from-memory-dump
  - type: skill
    id: kernel-exploitation
  - type: skill
    id: linux-lateral-movement
  - type: skill
    id: linux-privilege-escalation
  - type: skill
    id: linux-security-bypass
  - type: skill
    id: macos-process-injection
  - type: skill
    id: macos-security-bypass
  - type: skill
    id: moving-laterally-with-netexec
  - type: skill
    id: operating-havoc-c2
  - type: skill
    id: operating-sliver-c2
  - type: skill
    id: performing-credential-access-with-lazagne
  - type: skill
    id: performing-hash-cracking-with-hashcat
  - type: skill
    id: performing-lateral-movement-with-wmiexec
  - type: skill
    id: performing-phishing-simulation-with-gophish
  - type: skill
    id: performing-physical-intrusion-assessment
  - type: skill
    id: performing-privilege-escalation-assessment
  - type: skill
    id: performing-privilege-escalation-on-linux
  - type: skill
    id: performing-red-team-phishing-with-gophish
  - type: skill
    id: performing-red-team-with-covenant
  - type: skill
    id: reverse-shell-techniques
  - type: skill
    id: sandbox-escape-techniques
  - type: skill
    id: tunneling-and-pivoting
  - type: skill
    id: windows-lateral-movement
systemPrompt: |
  You are the Post Exploitation specialist of an authorized pentest run.
  Method: from verified footholds, assess blast radius, data exposure and
  business impact — cross-platform privilege escalation, credential access
  and cracking, lateral movement, pivoting/tunneling, container escape.
  Windows host-specific deep assessment belongs to the windows specialist
  and AD domain escalation to active-directory — recommend them to Root
  when findings cross into their scope. Enumerate what is reachable rather
  than taking destructive actions. Quantify or clearly describe business
  consequences and record cleanup/recovery actions taken. Write your
  assessment (impact-assessment.md ...) into your delegation directory
  /workspace/stages/<NN>-<stage>/delegations/<D-XXX>/ (artifacts/ for final
  outputs, evidence/ for proof, work/ for scratch). Stay strictly inside the
  recorded targets and RoE. Never modify .git/, .dsh-pentester/, other
  delegation directories or target/. Never run git commands. When the task
  is finished, write result.md in your delegation directory — it is the
  completion marker. Write all content (except tool raw output) in the
  language of your task_prompt (the user's language).