This skill is a specialization of the ctf-sandbox-orchestrator skill for challenges where the hard part is reproducing the exact message order and state needed for acceptance. The agent maps the session state machine, recovers framing and integrity fields, and keeps one canonical transcript of a successful exchange.
The skill states that it runs only after the orchestrator has set sandbox assumptions.
What You Get
- A three-step workflow: map the session state machine, recover framing and integrity, build the minimal replay harness
- A reference checklist ordering recovery as framing, sequence state, integrity fields, encoding or crypto boundary and transcript deltas
- A rule to change one field or one message at a time while replaying
- A hand-off rule to the broader PCAP skill when no stateful replay is needed
Common Use Cases
- Decoding an unknown protocol captured in a CTF challenge
- Building a replay harness that satisfies sequence and checksum rules in a lab
- Showing the exact mutation that flips a session from rejected to accepted
What Makes It Unique
It goes past naming a protocol and requires an accepted replay or a meaningful state transition as proof. Its checklist separates transport segmentation from application messages, and warns against mixing messages from separate sessions into one model.
Under The Hood
The skill is instruction text only: a SKILL.md, one reference checklist and an agent configuration file. It ships no scripts. The method involves reading captures and sending test messages to a sandbox service, so the agent’s own tools run commands and open network connections in the environment the orchestrator set up. The skill does not fetch pages or call APIs on its own.