Competition Mailbox Abuse is a downstream skill of the CTF Sandbox Orchestrator. It applies when the decisive path in a challenge runs through mailbox behavior, consent flow or message-routing effects.
The agent decides whether the active path is phishing-to-consent, token-to-mailbox, rule-based persistence or transport-level rerouting. It keeps mailbox, identity and message-trace evidence tied to the same user, token or message ID, and reduces the result to the smallest mail effect that proves persistence, exfiltration or delegate access.
What You Get
- A quick start that classifies the mail path first
- A three-stage workflow: map the mail trust path, prove the mailbox effect, reduce to the decisive chain
- A checklist of consent, rule and message-trace surfaces
- A rule to separate possession of a token from the mailbox effect it enables
- A hand-off to the broader identity skill for host pivots or Kerberos acceptance
Common Use Cases
- Reading inbox and transport rules in a mail forensics challenge
- Explaining how a consent grant leads to access to a mailbox
- Aligning message IDs and timestamps across logs
- Telling a rule effect from a transport effect in observed mail flow
What Makes It Unique
It treats mail as a state-and-effect problem. Each rule or token must be matched to a concrete effect, such as silent forwarding or deletion, and shared mailbox permissions are checked for cases where the owner never logged in.
Under The Hood
The skill is instruction text only: the SKILL.md body, one reference checklist and a small agent config file that disables implicit invocation. It ships no scripts. The instructions tell the agent to analyze logs, mailbox settings and traces from the sandbox the user supplies, to reply in Simplified Chinese unless asked for English, and to run only after the orchestrator skill is active.