This skill is a specialization of the ctf-sandbox-orchestrator skill for challenges where the hard part is following a file from ingress through every parser, extractor, converter or deserializer that touches it. The agent preserves the original upload and each derived artifact separately and records filenames, MIME guesses, temp paths and parser choices.
The skill states that it runs only after the orchestrator has set sandbox assumptions.
What You Get
- A three-step workflow: map file ingress and derivation, trace parser and conversion boundaries, reduce to the decisive file chain
- A reference checklist for ingress details, derived artifacts and final consumers
- A rule to label the original file and each derivative separately
- A hand-off rule to the queue and worker skill when the chain becomes an async worker problem
Common Use Cases
- Tracing where an uploaded archive is extracted and which parser reads its members in a lab app
- Explaining which converter or deserializer a backend picks for a given file
- Comparing what client-side validation allows with what the backend parser does
What Makes It Unique
It treats the file as a path through several tools and asks for evidence at each boundary. Its listed pitfalls include looking only at the original upload while ignoring derived intermediates, and treating MIME or extension checks as proof of which parser runs.
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 sending files to a sandbox application, unpacking archives and reading temp files, so the agent’s own tools make requests, run commands and write files in the environment the orchestrator set up. The skill does not fetch pages or call APIs on its own.