Skip to content
SkillModel-led550 tokens in use

Competition Mailbox Abuse

A downstream CTF-sandbox skill for tracing mailbox rules, OAuth consent grants, forwarding, delegate access and message traces in enterprise mail evidence.

44,996 stars on the repository MIT Licensezhaoxuya520/reverse-skill · CTF-Sandbox-Orchestrator/competition-mailbox-abuse
git clone https://github.com/zhaoxuya520/reverse-skill.git
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Competition Mailbox Abuse costs

121tokens idle
550tokens in use
772tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure23/25
  • Examples3/15
  • Output7/15
  • Size15/15
  • Resources7/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity96
  • Maintenance72
  • Community72
  • Maturity28
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers